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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating acceptability or unacceptability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acceptable or unacceptable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bankası
    -0.45
    ตัวเอง
    -0.39
     pandémie
    -0.38
    focus
    -0.38
     store
    -0.38
     focus
    -0.38
     appunt
    -0.37
    <strong>
    -0.37
     herida
    -0.37
     vastaan
    -0.37
    POSITIVE LOGITS
     Acceptable
    1.07
    Acceptable
    1.03
     acceptable
    1.02
    acceptable
    1.01
     unacceptable
    0.91
    ceptable
    0.90
     tolerable
    0.79
    SourceChecksum
    0.78
     acceptability
    0.73
     permissible
    0.73
    Act Density 0.013%

    No Known Activations