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

    Neuronpedia

    INDEX
    Explanations

    the word "vers" at the end of a word

    oai_token-act-pair · gpt-3.5-turbo

    the word "vers" variations referring to different contexts or meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fra
    -0.72
    redo
    -0.72
    RAW
    -0.66
    ľ
    -0.65
    opathic
    -0.63
    AFTA
    -0.62
     Rite
    -0.61
    ENDED
    -0.60
    UGH
    -0.60
    CHR
    -0.59
    POSITIVE LOGITS
    atility
    1.19
    atile
    1.18
    erver
    1.03
    terday
    1.01
    hip
    1.01
    ystem
    0.97
    ibilities
    0.94
    theless
    0.94
    pect
    0.91
    kers
    0.90
    Act Density 0.012%

    No Known Activations