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

    Neuronpedia

    INDEX
    Explanations

    phrases that express excessive amounts or extremes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.82
    ArgsConstructor
    -0.76
    انيف
    -0.74
     Савезне
    -0.71
    contentLoaded
    -0.70
     beginnetje
    -0.69
    σιμοποι
    -0.67
     InputDecoration
    -0.67
     Lordships
    -0.66
    InteropServices
    -0.66
    POSITIVE LOGITS
    Too
    1.37
     Too
    1.35
    too
    1.30
     too
    1.28
     TOO
    1.17
    TOO
    1.10
     excessive
    1.07
     Excessive
    1.02
    hel
    1.00
    HELL
    0.94
    Act Density 0.069%

    No Known Activations