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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intent or purpose in relation to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.44
    vois
    -0.44
    SurfaceView
    -0.44
    clerview
    -0.43
    HandleFunc
    -0.42
     strtolower
    -0.41
     lands
    -0.41
     Schatz
    -0.41
     secretary
    -0.40
    ax
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.89
    為了
    0.87
    为了
    0.86
    CloseOperation
    0.81
     estekak
    0.79
    AutoScaleMode
    0.78
    énario
    0.78
     للاسماء
    0.77
    paravant
    0.76
     ब्रेकडाउन
    0.75
    Act Density 0.441%

    No Known Activations