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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases indicating specific conditions for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lev
    -0.78
    vec
    -0.77
    Typ
    -0.76
    BIP
    -0.71
    áµ
    -0.67
    caps
    -0.66
    STAR
    -0.66
    gay
    -0.64
    Catal
    -0.64
    OL
    -0.64
    POSITIVE LOGITS
    soever
    0.91
    wcsstore
    0.74
     sparing
    0.73
    uesday
    0.71
    formance
    0.71
     supplying
    0.68
     Tanks
    0.67
     resort
    0.66
     geographically
    0.65
    fy
    0.64
    Act Density 0.093%

    No Known Activations