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

    Neuronpedia

    INDEX
    Explanations

    actions and concepts related to conflict or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Forge
    -0.16
    CLS
    -0.15
    aises
    -0.15
    _flash
    -0.15
    actics
    -0.14
    eldo
    -0.14
     uns
    -0.14
    å¥ı
    -0.14
    лаÑĪ
    -0.13
    neau
    -0.13
    POSITIVE LOGITS
    able
    0.22
    ables
    0.19
    ssi
    0.18
    ABLE
    0.18
    ingly
    0.17
    inand
    0.17
    erve
    0.16
    ÂŃing
    0.15
    inf
    0.15
    apel
    0.15
    Act Density 0.013%

    No Known Activations