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

    Neuronpedia

    INDEX
    Explanations

    references to specific names, likely related to people's names or surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Everywhere
    -0.18
    zl
    -0.16
    cox
    -0.16
    reve
    -0.15
    ustomed
    -0.15
    intel
    -0.15
    avicon
    -0.14
    buch
    -0.14
    vig
    -0.14
    enson
    -0.14
    POSITIVE LOGITS
    eri
    0.20
    er
    0.19
    eration
    0.18
    porno
    0.15
    бÑĢÑı
    0.14
    ADDE
    0.14
    eria
    0.14
    bear
    0.14
    bilt
    0.14
    OLER
    0.14
    Act Density 0.041%

    No Known Activations