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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate likelihood or strong statements about events or situations

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

    quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.58
    PostInfinity
    -0.51
     Administrativna
    -0.49
    ValueStyle
    -0.48
    InstrumentedTest
    -0.48
    sidemargin
    -0.46
     utafitiHapana
    -0.45
    เภ
    -0.45
    Попис
    -0.45
    InjectAttribute
    -0.44
    POSITIVE LOGITS
    RTHOOK
    0.45
    PyExc
    0.41
    metheus
    0.40
    intenant
    0.40
    OwnProperty
    0.40
    Javadoc
    0.39
    tagHelperRunner
    0.39
    ühungen
    0.37
    __':
    0.36
    brot
    0.36
    Act Density 0.065%

    No Known Activations