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

    Neuronpedia

    INDEX
    Explanations

    terms related to opposites and reversals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckle
    -0.16
    ÙģÙĤ
    -0.16
    emax
    -0.16
    eller
    -0.15
    roll
    -0.15
    uck
    -0.15
     ÑĤÑĢÑĥда
    -0.14
    몬
    -0.14
    ανδ
    -0.14
    olt
    -0.14
    POSITIVE LOGITS
    /back
    0.17
     polarity
    0.17
    overs
    0.17
    oda
    0.16
    reation
    0.15
    IRE
    0.15
    /op
    0.15
    dbl
    0.15
    -facing
    0.15
    BAB
    0.15
    Act Density 0.073%

    No Known Activations