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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong personal opinions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ')):
    -0.71
    oredCriteria
    -0.70
    aarrggbb
    -0.69
     ")");
    -0.69
     ""));
    -0.68
    '))
    -0.68
    "])
    -0.68
     myſelf
    -0.67
     "));
    -0.67
    ClientSize
    -0.66
    POSITIVE LOGITS
     really
    1.03
    really
    1.02
     Really
    1.02
    Really
    0.96
     REALLY
    0.88
    Thing
    0.81
     vraiment
    0.80
     thing
    0.79
     THING
    0.78
     Thing
    0.74
    Act Density 0.148%

    No Known Activations