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

    Neuronpedia

    INDEX
    Explanations

    references to various subjects and themes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.19
    enant
    -0.15
     ske
    -0.14
    reeze
    -0.14
    atrix
    -0.14
    esters
    -0.14
    .allocate
    -0.14
    htub
    -0.14
    ês
    -0.13
    asco
    -0.13
    POSITIVE LOGITS
    eson
    0.17
    ATUS
    0.16
    away
    0.16
    enson
    0.15
     themselves
    0.15
     neler
    0.15
    uits
    0.14
    /features
    0.14
    uger
    0.14
    anna
    0.14
    Act Density 0.372%

    No Known Activations