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

    Neuronpedia

    INDEX
    Explanations

    titles and formatting of names in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eless
    -0.18
     Swinger
    -0.17
    avir
    -0.17
    озд
    -0.16
    iless
    -0.15
     Monter
    -0.15
    iyas
    -0.15
     bul
    -0.14
    ango
    -0.14
     recl
    -0.14
    POSITIVE LOGITS
    alion
    0.16
    ÄĽl
    0.15
    .ua
    0.15
    witch
    0.15
    ÙĪÙĦÛĮ
    0.14
    ostÃŃ
    0.14
    anel
    0.13
    934
    0.13
    PHA
    0.13
    >e
    0.13
    Act Density 0.343%

    No Known Activations