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

    Neuronpedia

    INDEX
    Explanations

    conditional or contrasting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GIH
    -0.60
    UnusedPrivate
    -0.60
    InvalidProtocol
    -0.57
    PRNewswire
    -0.54
    wapV
    -0.53
    <bos>
    -0.51
    stdc
    -0.50
     Exacts
    -0.50
    HttpDelete
    -0.48
    undef
    -0.48
    POSITIVE LOGITS
    EndContext
    0.73
     зато
    0.72
     sí
    0.70
     כן
    0.70
    sizeCache
    0.70
     certainly
    0.69
     Tatsache
    0.64
     some
    0.62
    certainly
    0.62
    PhysRevD
    0.61
    Act Density 0.263%

    No Known Activations