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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of concern about various topics

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

    Comes before "at", "on", "going", or "wrong"

    np_acts-logits-general · gemini-2.0-flash

    what's it asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whom
    -0.59
    CreateMap
    -0.57
    الدراسه
    -0.54
     нещо
    -0.52
    whatever
    -0.51
    Whatever
    -0.51
     qualcosa
    -0.51
    whether
    -0.51
    erunner
    -0.50
    geordnet
    -0.50
    POSITIVE LOGITS
     happening
    1.25
     wrong
    1.11
     Happening
    0.81
     going
    0.81
    wrong
    0.78
     missing
    0.75
     required
    0.74
     needed
    0.74
     bothering
    0.73
     WRONG
    0.71
    Act Density 0.137%

    No Known Activations