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

    Neuronpedia

    INDEX
    Explanations

    statements about rules, principles, or guidelines that do not apply in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppe
    -0.16
     voks
    -0.14
    erus
    -0.14
    ijkstra
    -0.14
    asse
    -0.13
    ToFront
    -0.13
    ê±°ëŀĺê°Ģ
    -0.13
    pel
    -0.13
    eken
    -0.13
    olut
    -0.12
    POSITIVE LOGITS
     applies
    1.07
     apply
    1.07
    apply
    0.98
     Apply
    0.94
    Apply
    0.90
    .apply
    0.88
     applying
    0.87
     APPLY
    0.84
     applied
    0.84
     Applies
    0.82
    Act Density 0.366%

    No Known Activations