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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions within sentences that indicate agreement or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of agreements or commitments in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encount
    -0.54
     lately
    -0.52
    lihood
    -0.49
     potentially
    -0.48
    Interested
    -0.48
     showcased
    -0.47
     wherein
    -0.47
     Seeking
    -0.46
     frustrations
    -0.45
     grievances
    -0.45
    POSITIVE LOGITS
    only
    0.59
    cise
    0.56
    second
    0.54
    ãĥİ
    0.52
     entire
    0.51
    chal
    0.50
    iless
    0.49
    alogue
    0.48
    vag
    0.47
     Alone
    0.47
    Act Density 0.954%

    No Known Activations