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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or adverbs that amplify the degree of a quality or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dépos
    -0.61
    Very
    -0.57
     sempre
    -0.53
     tamamen
    -0.52
     bambou
    -0.51
    very
    -0.51
     foarte
    -0.51
    baz
    -0.50
     fær
    -0.50
     davvero
    -0.50
    POSITIVE LOGITS
     powerful
    0.78
     strong
    0.75
     strict
    0.70
    ieur
    0.69
     important
    0.68
     prominent
    0.68
     stringent
    0.66
     good
    0.66
     significant
    0.64
     tight
    0.64
    Act Density 0.465%

    No Known Activations