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

    Neuronpedia

    INDEX
    Explanations

    references to actions and relationships that involve change or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyen
    -0.17
    æŁ´
    -0.17
    aversable
    -0.15
     GRA
    -0.15
    AVE
    -0.14
    ave
    -0.14
    igid
    -0.14
    raz
    -0.14
    Advance
    -0.14
    arkin
    -0.14
    POSITIVE LOGITS
    oni
    0.18
    ousse
    0.15
    dyn
    0.15
    asi
    0.15
    ationally
    0.15
    anta
    0.14
     itself
    0.14
    elves
    0.14
    asso
    0.14
     custom
    0.13
    Act Density 0.001%

    No Known Activations