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

    Neuronpedia

    INDEX
    Explanations

    references to code functionality and programming issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebek
    -0.15
     Ñħол
    -0.15
    hol
    -0.14
    ави
    -0.14
     flesh
    -0.14
    arella
    -0.14
    _NC
    -0.14
    .strict
    -0.14
    oldem
    -0.14
    inski
    -0.14
    POSITIVE LOGITS
     zwar
    0.20
     superficial
    0.20
     overall
    0.18
     nomin
    0.18
    Aware
    0.18
     plenty
    0.17
    alom
    0.17
     lip
    0.16
    adox
    0.16
    overall
    0.16
    Act Density 0.278%

    No Known Activations