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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reflective thinking or introspection

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Angola
    -0.63
     Friendly
    -0.62
     Fine
    -0.61
    dding
    -0.60
    idon
    -0.59
    mobile
    -0.59
    Band
    -0.59
    ority
    -0.57
    ggies
    -0.57
    cox
    -0.56
    POSITIVE LOGITS
    alian
    0.94
    chy
    0.87
     transpired
    0.86
    asca
    0.84
     pains
    0.83
     beh
    0.82
    unes
    0.82
     rains
    0.79
     happened
    0.78
     boils
    0.77
    Act Density 0.123%

    No Known Activations