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

    Neuronpedia

    INDEX
    Explanations

    references to experimental conditions involving exposure and treatment durations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.78
    DockStyle
    -0.77
    Geplaatst
    -0.66
    PYX
    -0.62
    UnusedPrivate
    -0.62
    StructEnd
    -0.62
     Савезне
    -0.61
    buttonStyle
    -0.60
    WebVitals
    -0.60
     tartalomajánló
    -0.60
    POSITIVE LOGITS
     pre
    0.62
    PRE
    0.60
     pré
    0.58
     Pre
    0.56
    pre
    0.55
    Pre
    0.54
     PRE
    0.54
    预
    0.49
     préalable
    0.47
    あら
    0.46
    Act Density 0.010%

    No Known Activations