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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a degree of necessity or sufficiency

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.68
    تقاوى
    -0.63
    RenderAtEndOf
    -0.62
     فريبيس
    -0.60
    ">—
    -0.59
    gyi
    -0.56
     חיצוניים
    -0.56
    Hochspringen
    -0.53
    
    -0.53
    principalColumn
    -0.53
    POSITIVE LOGITS
    __))
    0.58
    SPATH
    0.53
     hinaus
    0.52
    jątk
    0.51
    MarshalTo
    0.50
    chitis
    0.50
    RTRS
    0.50
     SwitchCompat
    0.49
     TextAppearance
    0.47
    SourceChecksum
    0.47
    Act Density 0.225%

    No Known Activations