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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Mal" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edly
    -0.16
     entr
    -0.15
    ãĥªãĥ³ãĤ°
    -0.15
    skirts
    -0.15
    amb
    -0.14
    skou
    -0.14
    oton
    -0.14
    sel
    -0.14
    sharp
    -0.14
    elle
    -0.14
    POSITIVE LOGITS
    colm
    0.26
    nutrition
    0.26
    dives
    0.23
    gré
    0.23
    practice
    0.22
    tes
    0.21
    awi
    0.20
    vern
    0.20
    foy
    0.20
    aysia
    0.20
    Act Density 0.007%

    No Known Activations