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

    Neuronpedia

    INDEX
    Explanations

    words related to contrast or options

    oai_token-act-pair · gpt-3.5-turbo

    conditional or qualifying phrases in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.55
    iatus
    -0.50
    eno
    -0.48
    Newsletter
    -0.47
    enium
    -0.47
    enger
    -0.46
    Reply
    -0.46
    aley
    -0.44
     Millennium
    -0.43
    edge
    -0.43
    POSITIVE LOGITS
     preferably
    0.60
    éĹĺ
    0.56
    anwhile
    0.50
    cause
    0.50
    christ
    0.48
     notwithstanding
    0.48
    fortunately
    0.48
    conservancy
    0.47
     evidenced
    0.47
    ardless
    0.46
    Act Density 2.133%

    No Known Activations