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

    Neuronpedia

    INDEX
    Explanations

    medical terms related to conditions or diseases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guilt" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compr
    -0.74
    lished
    -0.73
    EStream
    -0.67
    ©¶æ
    -0.67
     gobl
    -0.66
    oÄŁ
    -0.66
    ccording
    -0.66
    BOOK
    -0.65
    linux
    -0.65
    İĭ
    -0.64
    POSITIVE LOGITS
    espie
    1.39
    uminati
    1.35
    iard
    1.15
    icit
    1.09
    inois
    1.04
    omon
    0.97
    ustration
    0.97
    umin
    0.95
    igan
    0.94
    usions
    0.93
    Act Density 0.027%

    No Known Activations