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

    Neuronpedia

    INDEX
    Explanations

    words related to the purpose or objective of something

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of purpose and motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.71
     weeds
    -0.68
     Leopard
    -0.67
     Isles
    -0.63
     juven
    -0.63
     Neighbor
    -0.62
     varieties
    -0.61
    Chance
    -0.60
    thumbnails
    -0.60
     Polo
    -0.60
    POSITIVE LOGITS
    ful
    1.39
    fully
    1.11
    fulness
    1.04
    FUL
    0.93
    lessly
    0.91
    lessness
    0.87
    full
    0.83
    ality
    0.82
    fare
    0.79
    bringer
    0.77
    Act Density 0.045%

    No Known Activations