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

    Neuronpedia

    INDEX
    Explanations

    adverbs that convey varying degrees of intensity or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adapt
    -0.56
     ند
    -0.55
    -
    -0.55
    al
    -0.53
    an
    -0.53
     limits
    -0.53
    us
    -0.52
    !
    -0.52
     marks
    -0.52
    ge
    -0.51
    POSITIVE LOGITS
    xically
    1.44
     weirdly
    1.24
     curiously
    1.20
    sively
    1.18
    ently
    1.17
     interestingly
    1.16
    iously
    1.15
     powerfully
    1.14
    ctively
    1.13
    tably
    1.13
    Act Density 0.343%

    No Known Activations