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

    Neuronpedia

    INDEX
    Explanations

    expressions related to societal observations and critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.84
    +#+#
    -0.84
    }>;
    -0.77
     démocr
    -0.77
    IntoConstraints
    -0.76
     '\\;'
    -0.75
     صوتيه
    -0.73
     propOrder
    -0.72
     itſelf
    -0.70
     betweenstory
    -0.69
    POSITIVE LOGITS
     who
    1.13
     whom
    1.06
     those
    1.04
     quienes
    0.93
    who
    0.90
    Those
    0.88
     Those
    0.88
    those
    0.87
    whom
    0.80
     ceux
    0.75
    Act Density 0.494%

    No Known Activations