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

    Neuronpedia

    INDEX
    Explanations

    characters, symbols, or formatting that indicate placeholders or markers within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cooke
    -0.16
    ģn
    -0.15
    aida
    -0.15
    atables
    -0.15
     Cobra
    -0.15
    ALSE
    -0.15
    év
    -0.15
    .onError
    -0.14
     Circus
    -0.14
    ipeline
    -0.14
    POSITIVE LOGITS
    åĴ²
    0.19
    iew
    0.18
    IEW
    0.18
     UNESCO
    0.16
    oria
    0.16
    740
    0.16
    Patch
    0.15
    cha
    0.15
    nea
    0.15
    ince
    0.14
    Act Density 0.008%

    No Known Activations