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

    Neuronpedia

    INDEX
    Explanations

    words related to options or choices

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "or."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.72
    onday
    -0.69
     vulner
    -0.63
    ilton
    -0.59
    Nev
    -0.59
    DERR
    -0.57
    elong
    -0.57
    eryl
    -0.57
    pter
    -0.56
    berries
    -0.56
    POSITIVE LOGITS
    acle
    1.23
    chard
    1.21
    acles
    1.17
    Else
    1.15
    lando
    1.11
    acular
    1.08
    chid
    1.03
    phan
    0.96
    ific
    0.96
    nam
    0.93
    Act Density 0.033%

    No Known Activations