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

    Neuronpedia

    INDEX
    Explanations

    references to names and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uw
    -0.17
    enna
    -0.15
     bumps
    -0.15
    LocalizedMessage
    -0.15
    oli
    -0.14
    ilt
    -0.14
    otta
    -0.14
    ewing
    -0.14
    utom
    -0.14
    ecs
    -0.14
    POSITIVE LOGITS
    -caret
    0.16
    protect
    0.16
     Maz
    0.15
     Woodward
    0.15
     interv
    0.15
    chooser
    0.14
     Scarlet
    0.14
    /IP
    0.14
    ardash
    0.13
    _reserved
    0.13
    Act Density 0.284%

    No Known Activations