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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structure elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dafx
    -0.69
    ]));
    -0.68
    +:+
    -0.67
    PYX
    -0.65
    }")
    -0.65
    ")]
    -0.65
    ')],
    -0.63
    ReferenceEquals
    -0.62
    '):
    -0.60
     certe
    -0.59
    POSITIVE LOGITS
    ↵↵↵
    0.82
    ↵
    0.70
    ↵↵↵↵
    0.65
    ↵↵
    0.64
    ↵↵↵↵↵
    0.63
    ↵↵↵↵↵↵
    0.57
    ↵↵↵↵↵↵↵↵↵↵↵
    0.53
    ↵↵↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵↵↵↵↵
    0.50
    ↵↵↵↵↵↵↵↵
    0.50
    Act Density 0.083%

    No Known Activations