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

    Neuronpedia

    INDEX
    Explanations

    words related to performing actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "'");
    -0.78
     BoxFit
    -0.77
    RenderAtEndOf
    -0.75
     فريبيس
    -0.74
     النه
    -0.74
     Zat
    -0.71
    rangle
    -0.70
     credence
    -0.70
     Ceb
    -0.69
     Wachs
    -0.69
    POSITIVE LOGITS
     PERFORM
    1.91
     performed
    1.87
     perform
    1.81
     Perform
    1.77
     Performed
    1.68
     Performing
    1.67
     performing
    1.66
    Perform
    1.64
     performs
    1.60
    performed
    1.52
    Act Density 0.092%

    No Known Activations