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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities or counts of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating quantity or count

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inelli
    -0.71
     silence
    -0.65
    outer
    -0.64
    aimon
    -0.62
    gewater
    -0.59
     opacity
    -0.59
     majesty
    -0.57
     Correspond
    -0.56
    oras
    -0.56
     entirety
    -0.55
    POSITIVE LOGITS
     of
    1.00
    assian
    0.76
    Of
    0.71
    casts
    0.68
    enance
    0.67
    phal
    0.66
    of
    0.66
     thereof
    0.64
     Of
    0.63
    atical
    0.63
    Act Density 0.049%

    No Known Activations