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

    Neuronpedia

    INDEX
    Explanations

    directives related to enabling or disabling features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.15
     Eid
    -0.14
    .grpc
    -0.14
    -anchor
    -0.14
    ATRIX
    -0.14
    ราย
    -0.14
    REE
    -0.14
    larım
    -0.14
    ulaire
    -0.14
    RIX
    -0.13
    POSITIVE LOGITS
    /disable
    0.20
     dormant
    0.17
    ment
    0.17
    VertexAttribArray
    0.16
    ylan
    0.16
    é
    0.15
    123
    0.14
     verbose
    0.14
    365
    0.14
     True
    0.14
    Act Density 0.047%

    No Known Activations