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

    Neuronpedia

    INDEX
    Explanations

    terms related to collaborative works and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DISCLAIM
    -0.15
    rana
    -0.15
    ehir
    -0.15
    itan
    -0.14
    XE
    -0.14
     Fucking
    -0.14
    ajs
    -0.14
    fall
    -0.14
     Sant
    -0.14
    landa
    -0.14
    POSITIVE LOGITS
    boro
    0.15
    /XMLSchema
    0.14
    oks
    0.14
    ç¬
    0.14
    eries
    0.14
    seg
    0.13
    oso
    0.13
    SEG
    0.13
    ogy
    0.13
    rl
    0.13
    Act Density 0.473%

    No Known Activations