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

    Neuronpedia

    INDEX
    Explanations

    words related to inspiration or motivation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating motivation or inspiration by external factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ased
    -0.82
    rek
    -0.80
    ilet
    -0.76
    umbered
    -0.75
    ategories
    -0.74
    bourne
    -0.72
    aping
    -0.72
     transitioned
    -0.71
    ape
    -0.71
    kered
    -0.70
    POSITIVE LOGITS
     virtue
    0.94
     sheer
    0.76
     mobs
    0.73
     nature
    0.72
     afar
    0.71
     combining
    0.68
     leaps
    0.67
     Viz
    0.67
    laws
    0.66
     Almighty
    0.66
    Act Density 0.076%

    No Known Activations