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

    Neuronpedia

    INDEX
    Explanations

    descriptions of potential outcomes or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential outcomes or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    displayText
    -0.63
    ĸļ
    -0.56
    @#&
    -0.52
    ogie
    -0.49
     sanitation
    -0.48
    ãĤ«
    -0.48
    sels
    -0.47
     Bless
    -0.46
    EH
    -0.46
    Reply
    -0.45
    POSITIVE LOGITS
     someday
    1.18
     sooner
    0.82
     somew
    0.78
     anytime
    0.72
    ivably
    0.72
     sometime
    0.71
     depending
    0.71
    depending
    0.70
     tomorrow
    0.67
     rethink
    0.66
    Act Density 1.862%

    No Known Activations