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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss restrictions or conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bridegroom
    -0.54
     convent
    -0.52
     Guarda
    -0.52
    menus
    -0.49
    boton
    -0.49
    rophore
    -0.48
    rasz
    -0.48
     PLWABN
    -0.48
    ghijklmnop
    -0.48
     aggro
    -0.48
    POSITIVE LOGITS
     limitations
    0.96
    limitations
    0.91
     limitation
    0.87
     Limitations
    0.87
    Limitations
    0.77
    TagMode
    0.72
    initComponents
    0.71
    AndEndTag
    0.71
    enderror
    0.70
    ViewFeatures
    0.69
    Act Density 0.001%

    No Known Activations