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

    Neuronpedia

    INDEX
    Explanations

    expressions of indifference or lack of regard for important subjects

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

    indifference and disregard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.75
     فريبيس
    -0.69
    Personensuche
    -0.64
     سكانية
    -0.60
    RTEX
    -0.59
    Personendaten
    -0.59
    ckså
    -0.59
    principalColumn
    -0.59
     esternos
    -0.59
     enfans
    -0.59
    POSITIVE LOGITS
     disregard
    0.76
     ignore
    0.65
     disregarded
    0.64
     ignored
    0.63
     indifference
    0.63
     disregarding
    0.58
     ignoring
    0.58
     ignor
    0.57
     ignores
    0.56
     Ignore
    0.56
    Act Density 0.036%

    No Known Activations