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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb 'to be.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.73
     Reduce
    -0.73
     membr
    -0.70
     mater
    -0.67
    TAIN
    -0.67
    DS
    -0.63
    andise
    -0.63
    acters
    -0.59
     occurs
    -0.59
     denotes
    -0.59
    POSITIVE LOGITS
     gonna
    1.52
     gotta
    1.15
     going
    1.04
     hoping
    1.03
     glad
    1.00
     sorry
    0.99
     afraid
    0.96
     guessing
    0.96
     supposed
    0.94
     got
    0.93
    Act Density 0.052%

    No Known Activations