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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "At"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borg
    -0.17
    spo
    -0.17
     Porno
    -0.15
     ï½ľ
    -0.15
    ammen
    -0.15
    Ĭ
    -0.15
     Seks
    -0.14
     boj
    -0.14
    upo
    -0.14
    vern
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.17
    ella
    0.15
    atan
    0.15
    _dispatch
    0.15
    bable
    0.15
    imax
    0.14
    xit
    0.14
    tres
    0.13
    zar
    0.13
    idge
    0.13
    Act Density 0.005%

    No Known Activations