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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech and quotations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.17
    :
    -0.15
    akin
    -0.15
    ãĥ¼ãĥij
    -0.14
    :The
    -0.14
     Barrett
    -0.14
     Bench
    -0.13
    ench
    -0.13
    /apis
    -0.13
    è³¢
    -0.13
    POSITIVE LOGITS
    åıĤçħ§
    0.16
    uess
    0.15
    ancel
    0.15
    anzi
    0.15
     regarding
    0.15
    714
    0.15
    ombat
    0.14
    BuilderInterface
    0.14
    Ľå»º
    0.13
    ouro
    0.13
    Act Density 0.047%

    No Known Activations