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

    Neuronpedia

    INDEX
    Explanations

    intensifying adjectives that emphasize degree or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.73
     sauvages
    -0.72
     sepenuhnya
    -0.69
     complètes
    -0.67
     culoare
    -0.66
    paravant
    -0.66
     religieuses
    -0.65
     ooit
    -0.65
     européennes
    -0.64
     eterno
    -0.63
    POSITIVE LOGITS
     much
    0.75
    thing
    0.73
    THING
    0.65
     few
    0.64
     surla
    0.64
     likely
    0.61
     rarely
    0.60
    rare
    0.60
    much
    0.58
    IntoConstraints
    0.55
    Act Density 0.061%

    No Known Activations