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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" and related phrases indicating singularity or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.15
    nement
    -0.15
    اÙģت
    -0.15
    pany
    -0.15
    agnost
    -0.14
     kles
    -0.14
    rador
    -0.14
    оказ
    -0.14
    oload
    -0.14
    ../../
    -0.14
    POSITIVE LOGITS
    tery
    0.16
    esk
    0.16
    enga
    0.15
    vt
    0.14
    es
    0.14
    ViewHolder
    0.13
    olla
    0.13
    ält
    0.13
     Wich
    0.13
     Ø£Ùħر
    0.13
    Act Density 0.044%

    No Known Activations