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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases and expressions of confusion or uncertainty

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

    asking questions or seeking clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.58
    imageshack
    -0.54
    oa̍t
    -0.54
    GTCX
    -0.50
    StreetMap
    -0.46
    ⋱
    -0.45
    bcryptjs
    -0.45
    hyrchwyd
    -0.44
    ()]
    -0.44
     ویکی‌پدی
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.49
     consultato
    0.42
    AccessorTable
    0.41
     féminine
    0.41
     perigo
    0.37
     recoge
    0.36
     exposição
    0.35
     peligro
    0.35
     CreateTagHelper
    0.35
    RefNanny
    0.35
    Act Density 0.298%

    No Known Activations