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

    Neuronpedia

    INDEX
    Explanations

    words related to aggression and friendliness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     asciug
    -0.78
    issipp
    -0.73
    <h5>
    -0.69
     inset
    -0.68
    awtextra
    -0.68
    Moments
    -0.68
    zeug
    -0.67
    setof
    -0.67
    gefügt
    -0.67
     limone
    -0.66
    POSITIVE LOGITS
     agres
    1.00
     aggres
    0.94
     aggressive
    0.92
     hostile
    0.92
     hostility
    0.91
     aggressiveness
    0.89
    aggressive
    0.85
     friendly
    0.84
     friendliness
    0.82
     Friendly
    0.82
    Act Density 0.012%

    No Known Activations