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

    Neuronpedia

    INDEX
    Explanations

    words related to themes, topics or characteristics that are dramatic or powerful in nature

    oai_token-act-pair · gpt-3.5-turbo

    words related to thematic elements in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.82
    ardless
    -0.72
    conn
    -0.72
    cloth
    -0.72
    pun
    -0.69
    lessness
    -0.69
    hig
    -0.69
    é¾įå
    -0.69
    ilts
    -0.67
    fman
    -0.67
    POSITIVE LOGITS
    atic
    0.83
    andum
    0.81
    ity
    0.74
    quished
    0.73
    onduct
    0.70
     acid
    0.68
     Emir
    0.68
    omatic
    0.68
     contrasts
    0.66
    anwhile
    0.65
    Act Density 0.021%

    No Known Activations