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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong personal conviction or stance on a topic

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing belief or conviction about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.81
    agher
    -0.67
    pmwiki
    -0.65
    ammy
    -0.64
    practice
    -0.64
    effect
    -0.64
    umber
    -0.64
    housing
    -0.63
     Pavilion
    -0.61
    apeake
    -0.61
    POSITIVE LOGITS
     believe
    0.83
     believes
    0.74
    ieve
    0.74
    orean
    0.73
    orians
    0.73
    fulness
    0.72
    rill
    0.72
     BEL
    0.69
    ril
    0.67
    rils
    0.66
    Act Density 0.037%

    No Known Activations