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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases indicating roles or positions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahat
    -0.16
    ฺ
    -0.16
    uyên
    -0.16
    óng
    -0.16
    ovice
    -0.15
    ICY
    -0.15
    _POINTER
    -0.14
    missible
    -0.14
    porter
    -0.14
    xac
    -0.14
    POSITIVE LOGITS
     TRACE
    0.16
     Burton
    0.14
    ival
    0.14
    ubby
    0.14
    ika
    0.14
    sert
    0.13
     para
    0.13
     UsersController
    0.13
     retract
    0.13
    .openapi
    0.13
    Act Density 0.033%

    No Known Activations