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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities or incremental changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Prostit
    -0.16
     uncomment
    -0.15
    895
    -0.15
    rlen
    -0.15
    611
    -0.14
    877
    -0.14
    reek
    -0.14
    203
    -0.14
    ottom
    -0.14
    eck
    -0.14
    POSITIVE LOGITS
    ippi
    0.17
     Bernard
    0.16
    unik
    0.15
    esis
    0.15
    Undefined
    0.15
    ynet
    0.15
    è£ķ
    0.14
     Babe
    0.14
    itted
    0.14
    _CONF
    0.14
    Act Density 0.002%

    No Known Activations