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

    Neuronpedia

    INDEX
    Explanations

    conditional or contrasting clauses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jîn
    -0.66
    ANSA
    -0.64
    GMENT
    -0.63
    ruik
    -0.62
     AllMusic
    -0.62
    gypti
    -0.62
     decidedly
    -0.61
    Rujuakan
    -0.60
    TAWA
    -0.59
    прочем
    -0.59
    POSITIVE LOGITS
     it
    0.74
     the
    0.70
    很多的
    0.70
     majority
    0.67
     дан
    0.64
     there
    0.63
    Majority
    0.60
    nextProps
    0.59
     didalam
    0.58
     meeste
    0.58
    Act Density 0.501%

    No Known Activations