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

    Neuronpedia

    INDEX
    Explanations

    words related to technological terms or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ich" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.63
    ework
    -0.61
    0000000000000000
    -0.60
     logical
    -0.60
    ctica
    -0.59
     rall
    -0.59
     unrestricted
    -0.59
     accord
    -0.58
     Wass
    -0.58
    ¥µ
    -0.58
    POSITIVE LOGITS
    olson
    1.15
    icago
    1.04
    ynski
    1.03
    oice
    0.99
    rome
    0.98
    keye
    0.91
    thy
    0.90
    annel
    0.88
    orst
    0.88
    ards
    0.85
    Act Density 0.032%

    No Known Activations