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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rage" and related variations, indicating emotional intensity or outbursts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.83
    ramer
    -0.78
    arya
    -0.74
    metics
    -0.72
    rity
    -0.69
    icut
    -0.67
    leanor
    -0.67
    ournal
    -0.67
    icrobial
    -0.67
    roma
    -0.67
    POSITIVE LOGITS
    quit
    1.13
     raging
    0.95
     rage
    0.93
     fury
    0.92
    stru
    0.81
     raged
    0.80
     against
    0.79
    storms
    0.79
    ously
    0.78
     vengeance
    0.77
    Act Density 0.008%

    No Known Activations