Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to combining or unifying multiple things into a single entity or interface.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    phrases indicating singularity or simplicity in processes and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Refers to things being "single" or "unified"

    np_acts-logits-general · gemini-2.0-flash

    one and single units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aiheesta
    -0.30
    ril
    -0.30
     Panto
    -0.29
    MathML
    -0.29
    StartTag
    -0.29
     مُعرِّف
    -0.28
    ウダー
    -0.28
    lewati
    -0.27
     May
    -0.27
     duo
    -0.27
    POSITIVE LOGITS
     unified
    0.81
     unifying
    0.75
    Unified
    0.71
    unified
    0.71
    统一
    0.70
     Unified
    0.69
    統一
    0.64
     unify
    0.63
     unification
    0.62
     houſe
    0.61
    Act Density 0.329%

    No Known Activations