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

    Neuronpedia

    INDEX
    Explanations

    phrases related to encounters or interactions, particularly in the context of danger or risk

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

    experience danger

    np_acts-logits-general · gemini-2.5-flash-lite

    words signaling danger, urgent action, or necessity (emergency/risk contexts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Rozm
    -0.39
     kehilangan
    -0.36
    endimiento
    -0.35
     costes
    -0.33
     Verkehr
    -0.33
     permiso
    -0.32
     comigo
    -0.32
     habido
    -0.32
    ฤ
    -0.31
     tesettür
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.63
    舺
    0.60
    ↹
    0.60
     CreateTagHelper
    0.57
    UrlResolution
    0.53
    /**
    0.52
    ViewInit
    0.52
    Diweddarwch
    0.51
    devamını
    0.50
    RenderAtEndOf
    0.50
    Act Density 0.046%

    No Known Activations