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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to distortion or abnormality

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to distortion and corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.90
    ciation
    -0.90
    ufact
    -0.79
    cially
    -0.77
    worthiness
    -0.73
    pletion
    -0.73
    cial
    -0.73
    chall
    -0.73
    ILA
    -0.72
    agement
    -0.71
    POSITIVE LOGITS
     twisted
    0.95
     twisting
    0.93
     twist
    0.92
     twists
    0.85
     Hollow
    0.78
     Twisted
    0.77
     lengths
    0.75
     interpretations
    0.71
     versions
    0.69
     intertw
    0.68
    Act Density 0.013%

    No Known Activations