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

    Neuronpedia

    INDEX
    Explanations

    words related to specific scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "case" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elta
    -0.68
    zl
    -0.58
    aples
    -0.56
    incinn
    -0.55
    avorite
    -0.55
    izable
    -0.55
    ****************
    -0.54
    terday
    -0.54
    orously
    -0.53
    gets
    -0.53
    POSITIVE LOGITS
     of
    0.84
    osphere
    0.74
    of
    0.73
    pires
    0.67
     OF
    0.66
    pire
    0.66
     thereof
    0.61
    verse
    0.59
    ction
    0.58
    Ĥİ
    0.58
    Act Density 0.078%

    No Known Activations