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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation and judging processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchi
    -0.18
    .NewLine
    -0.16
    mour
    -0.15
    uchen
    -0.15
    çĮ®
    -0.14
    Tail
    -0.14
    è
    -0.14
    .idea
    -0.14
     Tail
    -0.14
     puff
    -0.14
    POSITIVE LOGITS
     decisions
    0.20
     decision
    0.18
     quyết
    0.18
     Decision
    0.17
    decision
    0.17
     evaluation
    0.16
    Decision
    0.16
     kararı
    0.16
     scor
    0.15
    ãĥ¬ãĥĵ
    0.15
    Act Density 0.150%

    No Known Activations