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

    Neuronpedia

    INDEX
    Explanations

    phrases and commands related to stopping or ceasing an action

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

    long live / stop at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.44
     Menschheit
    -0.39
     dramatique
    -0.35
     venezolano
    -0.35
     humanidade
    -0.34
     مشارکت‌کنندگان
    -0.33
     démocr
    -0.33
     пищи
    -0.33
     complètes
    -0.32
     assolu
    -0.32
    POSITIVE LOGITS
     noDo
    0.76
    帖最后由
    0.63
     MainAxisSize
    0.60
    LookAnd
    0.58
    abestanden
    0.57
    IVEREF
    0.57
     محفوظة
    0.56
    PyExc
    0.56
     gynnwys
    0.56
    RTEX
    0.55
    Act Density 0.050%

    No Known Activations