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

    Neuronpedia

    INDEX
    Explanations

    negative emotions or actions related to conflict and disappointment

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

    causing anger or displeasure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.47
    脚注の使い方
    -0.43
    Kjelder
    -0.42
    Hochspringen
    -0.40
     autorytatywna
    -0.39
    ">//
    -0.36
     Мексичка
    -0.36
    EndGlobalSection
    -0.36
    contentLoaded
    -0.35
    MetaObject
    -0.35
    POSITIVE LOGITS
    得罪
    0.67
     wrath
    0.56
    SequentialGroup
    0.54
     offend
    0.53
    Angry
    0.53
     inimigo
    0.52
     transgress
    0.51
    怒
    0.51
     offended
    0.50
     dépla
    0.49
    Act Density 0.074%

    No Known Activations