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

    Neuronpedia

    INDEX
    Explanations

    terms related to authorship or research papers

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

    Tokens starting with "Wo" and followed by certain letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with Wo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.75
     <>",
    -0.69
     Paglinawan
    -0.66
    LookAnd
    -0.66
    GOTREF
    -0.66
    principalTable
    -0.66
     nahilalakip
    -0.65
    Spoljašnje
    -0.63
    portál
    -0.63
    ConstraintMaker
    -0.63
    POSITIVE LOGITS
     Wo
    0.71
    vo
    0.69
    Wo
    0.66
     wo
    0.65
    voz
    0.64
    wo
    0.62
     față
    0.61
     vo
    0.60
     œuvres
    0.58
     Wohl
    0.58
    Act Density 0.120%

    No Known Activations