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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations or affirmations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "good" and its context related to positive outcomes or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eters
    -0.71
    gemony
    -0.71
     Strait
    -0.71
    oths
    -0.71
    fty
    -0.71
     Pavilion
    -0.69
    uthor
    -0.69
    opers
    -0.66
    edIn
    -0.66
    ategory
    -0.66
    POSITIVE LOGITS
    enough
    1.34
    bye
    1.22
     luck
    1.16
    reads
    1.15
     enough
    1.11
    luck
    1.10
     ol
    1.07
     Samar
    1.06
    night
    0.98
     Enough
    0.94
    Act Density 0.072%

    No Known Activations