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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reciprocal relationships or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essim
    -0.15
    ati
    -0.15
    loon
    -0.15
    _locals
    -0.14
    esel
    -0.14
    owell
    -0.14
    atu
    -0.14
    av
    -0.14
    uen
    -0.14
    uide
    -0.14
    POSITIVE LOGITS
     convers
    0.19
     vice
    0.18
    igne
    0.17
    VICE
    0.16
     Vice
    0.15
    vero
    0.15
    ajs
    0.15
     versa
    0.15
    etat
    0.15
    vice
    0.14
    Act Density 0.010%

    No Known Activations