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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and adjectives expressing strong feelings or levels of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     absolutely
    -0.16
     пÑĢекÑĢаÑģ
    -0.16
     utterly
    -0.15
     entirely
    -0.15
    better
    -0.15
     invariably
    -0.15
     endlessly
    -0.15
    Perfect
    -0.15
     totally
    -0.15
     Absolutely
    -0.15
    POSITIVE LOGITS
     much
    0.31
    much
    0.26
     few
    0.26
    thing
    0.23
     little
    0.23
     Much
    0.23
     rarely
    0.23
     seldom
    0.22
     soon
    0.21
    yyy
    0.21
    Act Density 0.075%

    No Known Activations