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

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotional reactions and societal observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }*/
    -0.56
    '}>
    -0.53
    ltä
    -0.52
    ocl
    -0.52
    ')['
    -0.49
    })();
    -0.49
    })();
    -0.47
    __':
    -0.47
     Disponible
    -0.46
    })*/
    -0.46
    POSITIVE LOGITS
    IVEREF
    0.70
    YYY
    0.68
    TTTT
    0.67
    SSS
    0.65
    YYYY
    0.65
     THOUGH
    0.64
    LLLL
    0.63
     صوتيه
    0.62
    DDDD
    0.60
    NNNN
    0.59
    Act Density 0.139%

    No Known Activations