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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating knowledge or familiarity with a topic

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating shared knowledge or common understanding among the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oreal
    -0.80
    cific
    -0.73
    ngth
    -0.69
     streng
    -0.69
    rontal
    -0.68
    vati
    -0.67
    orthy
    -0.66
    ongevity
    -0.65
    ihad
    -0.64
    bably
    -0.64
    POSITIVE LOGITS
    tale
    0.76
     about
    0.68
     how
    0.67
     that
    0.67
     by
    0.63
     why
    0.60
    anton
    0.59
     tales
    0.58
     Ced
    0.57
     what
    0.56
    Act Density 0.126%

    No Known Activations