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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to stopping or pausing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixa
    -0.15
    antic
    -0.14
     kostenlose
    -0.14
    errat
    -0.14
    enced
    -0.14
    ikh
    -0.14
     intens
    -0.14
    ulfill
    -0.14
     feu
    -0.14
    zar
    -0.14
    POSITIVE LOGITS
    ocker
    0.17
     Generation
    0.17
    690
    0.16
    /Branch
    0.15
    azzo
    0.15
    ftar
    0.15
     شاخÙĩ
    0.15
     à¤ªà¥ľ
    0.15
    Ú¯Ùĩ
    0.15
     poz
    0.14
    Act Density 0.076%

    No Known Activations