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

    Neuronpedia

    INDEX
    Explanations

    references to data, statistics, or quantifiable outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erve
    -0.16
     Dit
    -0.16
     UIL
    -0.15
    issan
    -0.15
    yx
    -0.15
    tid
    -0.15
    ariat
    -0.14
    dit
    -0.14
    ander
    -0.14
     leg
    -0.14
    POSITIVE LOGITS
    @student
    0.17
    CTest
    0.17
    incer
    0.15
    uddy
    0.15
    FFFF
    0.14
    úp
    0.14
    igon
    0.14
    (strict
    0.14
    quat
    0.14
    커ìĬ¤
    0.14
    Act Density 0.020%

    No Known Activations