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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that explore hypothetical scenarios

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

    what if

    np_acts-logits-general · gemini-2.5-flash-lite

    Sentences or phrases that introduce hypothetical questions or "what if" style counterfactuals.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.43
     remonter
    -0.42
    出版年
    -0.37
     kasarigan
    -0.36
     zdrowia
    -0.36
    ConstraintMaker
    -0.35
    Referências
    -0.35
     suyo
    -0.35
     jadx
    -0.35
     kialak
    -0.35
    POSITIVE LOGITS
    MessageOf
    0.63
    KommentareTeilen
    0.50
     Италијани
    0.47
     linkovi
    0.46
    webElementGuid
    0.44
    ser
    0.44
    ніципа
    0.43
    怎麼辦
    0.43
    iastes
    0.43
    TintMode
    0.43
    Act Density 0.201%

    No Known Activations