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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of doubt in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.90
    ς
    -0.47
    ی
    -0.45
    の
    -0.43
     Verhält
    -0.41
    י
    -0.41
    es
    -0.41
    ים
    -0.41
    .
    -0.40
     whose
    -0.40
    POSITIVE LOGITS
    <bos>
    0.82
     незавершена
    0.60
     kaarangay
    0.58
    SourceChecksum
    0.56
    AccessorTable
    0.55
    findpost
    0.55
     препратки
    0.54
     Superhost
    0.54
    ſicht
    0.52
     виправивши
    0.51
    Act Density 0.102%

    No Known Activations