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

    Neuronpedia

    INDEX
    Explanations

    references to nesting behavior and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    295
    -0.18
    631
    -0.16
    oz
    -0.15
    ancellationToken
    -0.14
    ollider
    -0.14
    óz
    -0.14
    одейÑģÑĤв
    -0.14
     Oz
    -0.14
    avage
    -0.14
    SenderId
    -0.13
    POSITIVE LOGITS
    ÑĢам
    0.16
    nest
    0.15
    eh
    0.15
    _singleton
    0.15
    ekte
    0.15
    ylie
    0.15
    (strtolower
    0.14
     hi
    0.14
    onde
    0.14
    pond
    0.14
    Act Density 0.008%

    No Known Activations