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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidelines and applicability of rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppe
    -0.14
     voks
    -0.14
    ê±°ëŀĺê°Ģ
    -0.14
    ittel
    -0.14
    pel
    -0.14
    ijkstra
    -0.13
    eken
    -0.13
    ingham
    -0.13
    kit
    -0.13
    okia
    -0.13
    POSITIVE LOGITS
     applies
    1.04
     apply
    1.01
    apply
    0.93
     Apply
    0.89
    Apply
    0.85
    .apply
    0.84
     applying
    0.83
     APPLY
    0.79
     Applies
    0.79
     applied
    0.75
    Act Density 0.337%

    No Known Activations