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

    Neuronpedia

    INDEX
    Explanations

    words related to themes or motifs

    oai_token-act-pair · gpt-3.5-turbo

    words related to thematic elements and motifs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.84
    enegger
    -0.82
    lessness
    -0.81
    fman
    -0.78
    hig
    -0.75
    Downloadha
    -0.73
    cloth
    -0.72
    shire
    -0.70
    jar
    -0.69
    pun
    -0.68
    POSITIVE LOGITS
    andum
    0.88
    ity
    0.87
    onduct
    0.86
    henko
    0.77
    idal
    0.71
     acid
    0.71
    atic
    0.69
    acia
    0.69
    omatic
    0.69
    olor
    0.67
    Act Density 0.038%

    No Known Activations