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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states of being

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or the word "are" related to collective identity or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odder
    -0.74
    ulence
    -0.67
    rouse
    -0.63
    ademic
    -0.63
     disappears
    -0.62
    odor
    -0.62
    fulness
    -0.62
    coon
    -0.61
    icist
    -0.61
    cu
    -0.61
    POSITIVE LOGITS
     ourselves
    1.15
     thankful
    1.11
     glad
    1.03
     fortunate
    1.00
     grateful
    1.00
     witnessing
    0.95
     pioneers
    0.94
     proud
    0.93
     gonna
    0.92
     indebted
    0.92
    Act Density 0.176%

    No Known Activations