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

    Neuronpedia

    INDEX
    Explanations

    references to technical exceptions and code implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unya
    -0.19
    autoload
    -0.14
    icha
    -0.14
     Retrie
    -0.14
    mj
    -0.14
     mote
    -0.14
    formance
    -0.14
     convers
    -0.14
     Gang
    -0.13
    rez
    -0.13
    POSITIVE LOGITS
    CAF
    0.16
    uma
    0.15
    addr
    0.15
    seg
    0.15
    ulin
    0.14
    jom
    0.14
    aus
    0.14
    .bid
    0.14
    anova
    0.14
     seg
    0.14
    Act Density 0.004%

    No Known Activations