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

    Neuronpedia

    INDEX
    Explanations

    language related to retaliation and aggressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervo
    -0.15
     OVERRIDE
    -0.14
    anki
    -0.14
    okud
    -0.14
    ütün
    -0.14
    unan
    -0.13
    ica
    -0.13
    YNAM
    -0.13
    ImageContext
    -0.13
    isÃŃ
    -0.13
    POSITIVE LOGITS
     against
    0.38
    against
    0.31
     Against
    0.29
    Against
    0.27
     for
    0.24
    æݪæĸ½
    0.21
     gegen
    0.19
     measures
    0.19
     tegen
    0.19
     Measures
    0.19
    Act Density 0.026%

    No Known Activations