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

    Neuronpedia

    INDEX
    Explanations

    references to specific parameters and their relationships within structured data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    527
    -0.20
    igan
    -0.14
     Rotation
    -0.14
    mund
    -0.14
    ica
    -0.14
    ICA
    -0.13
     rotation
    -0.13
     Thumb
    -0.13
     Cann
    -0.13
    orama
    -0.13
    POSITIVE LOGITS
    acente
    0.17
    alto
    0.16
     otherwise
    0.16
    ÃľR
    0.15
    ritten
    0.15
    chez
    0.14
     FileAccess
    0.14
    atör
    0.14
    cro
    0.14
    acin
    0.14
    Act Density 0.250%

    No Known Activations