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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of letters that correspond to names or identifiers

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

    words starting with W

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qrst
    -0.51
    TemporalType
    -0.50
    tagHelper
    -0.46
    anyeol
    -0.44
    permitAll
    -0.44
     Kild
    -0.42
     raí
    -0.41
    idiv
    -0.41
    .*")]
    -0.40
    MENAFN
    -0.40
    POSITIVE LOGITS
    wak
    0.69
    ww
    0.69
    wo
    0.68
    wat
    0.67
    waf
    0.66
    wed
    0.66
    w
    0.65
     שוליים
    0.65
    wc
    0.64
    wy
    0.63
    Act Density 0.056%

    No Known Activations