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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain significant numerical or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /**
    -0.92
     nakalista
    -0.91
     AssemblyCulture
    -0.91
    +#+#
    -0.90
    InjectAttribute
    -0.90
     bezeichneter
    -0.88
     pleaſure
    -0.85
     BoxDecoration
    -0.83
    WebVitals
    -0.82
     تانيه
    -0.81
    POSITIVE LOGITS
    “
    0.82
    ↵↵
    0.69
    [toxicity=0]
    0.65
     “
    0.64
    ↵↵↵
    0.58
    ↵
    0.57
    ?
    0.57
    ‘
    0.57
    *
    0.56
    (
    0.56
    Act Density 0.170%

    No Known Activations