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

    Neuronpedia

    INDEX
    Explanations

    words that indicate alternatives or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Griffith
    -0.69
     Wiseman
    -0.66
    unay
    -0.59
    enheim
    -0.58
     Uli
    -0.57
    Vivian
    -0.56
    bang
    -0.54
    rishnan
    -0.54
    Ƚ
    -0.54
     highlights
    -0.54
    POSITIVE LOGITS
     Either
    2.10
    Either
    2.08
     either
    2.05
    either
    2.00
    ITHER
    1.69
     entweder
    1.65
    ither
    1.26
     enten
    1.26
    weder
    1.23
    要么
    1.08
    Act Density 0.064%

    No Known Activations