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

    Neuronpedia

    INDEX
    Explanations

    verbs that describe a significant change or increase

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating rapid or significant changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.71
    oute
    -0.66
    rys
    -0.64
     privilege
    -0.63
    rite
    -0.63
    IRO
    -0.62
    ym
    -0.62
    oked
    -0.61
    pron
    -0.59
     ACL
    -0.57
    POSITIVE LOGITS
     srfAttach
    0.84
     ILCS
    0.84
     during
    0.78
     throughout
    0.76
     (>
    0.75
     afterwards
    0.74
     afterward
    0.73
    utics
    0.73
     because
    0.72
     thereafter
    0.72
    Act Density 0.184%

    No Known Activations