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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the intended purpose or function of objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "purpose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weeds
    -0.71
    etts
    -0.69
     Wolves
    -0.66
     Leopard
    -0.66
    thumbnails
    -0.65
     Thumbnails
    -0.65
     Polo
    -0.64
     Ashes
    -0.63
     Oaks
    -0.62
     Temper
    -0.62
    POSITIVE LOGITS
    ful
    1.26
    lessly
    1.04
    ality
    0.98
    lessness
    0.98
    fully
    0.98
    tenance
    0.95
    fulness
    0.94
    eous
    0.88
    FUL
    0.87
    teness
    0.85
    Act Density 0.023%

    No Known Activations