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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging experimentation or attempts at new activities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     attempt
    -0.85
     attempts
    -0.84
     Attempt
    -0.81
     Olsen
    -0.77
     attempting
    -0.77
     Mocking
    -0.76
    مراجع
    -0.75
    attempts
    -0.75
    RenderAtEndOf
    -0.72
     Attempts
    -0.72
    POSITIVE LOGITS
    wamy
    0.60
     Trasp
    0.59
    fly
    0.58
    homonymie
    0.57
     propOrder
    0.57
    ority
    0.54
    ilkan
    0.54
    iteracy
    0.54
    wir
    0.54
    featureID
    0.54
    Act Density 0.028%

    No Known Activations