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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives that convey intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.39
     estético
    -0.39
    lorette
    -0.38
     femenino
    -0.34
    jsii
    -0.33
     asiática
    -0.33
    gridx
    -0.33
     talent
    -0.32
     '\\;'
    -0.32
    มาย
    -0.32
    POSITIVE LOGITS
    powerful
    0.96
     powerful
    0.95
     Powerful
    0.90
    Powerful
    0.86
     poderosa
    0.78
     poderoso
    0.76
     puissante
    0.76
     powerfully
    0.75
     poderosos
    0.75
    powered
    0.73
    Act Density 0.088%

    No Known Activations