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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating relationships or functions related to the subject being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    766
    -0.20
     it
    -0.18
     оно
    -0.18
    erif
    -0.16
    ilk
    -0.16
    poons
    -0.16
    OrFail
    -0.15
    ña
    -0.15
    yms
    -0.15
    å®ĥ
    -0.15
    POSITIVE LOGITS
    iner
    0.20
    aly
    0.18
    /boot
    0.18
    oleon
    0.18
    913
    0.17
    ouz
    0.17
    anken
    0.16
     Vend
    0.16
    £
    0.16
    353
    0.15
    Act Density 0.023%

    No Known Activations