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

    Neuronpedia

    INDEX
    Explanations

    code snippets and elements in a structured document format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gra
    -0.16
     gaz
    -0.16
     antic
    -0.16
     accompanied
    -0.15
    orum
    -0.15
    gen
    -0.14
     Parliament
    -0.14
    uga
    -0.14
     ind
    -0.14
    ays
    -0.14
    POSITIVE LOGITS
    incerely
    0.18
    iele
    0.17
    akte
    0.15
     поба
    0.15
    incer
    0.14
    quito
    0.14
    itur
    0.14
    izio
    0.14
    avig
    0.14
    adece
    0.14
    Act Density 0.032%

    No Known Activations