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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to rankings or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    topp
    -0.47
     rama
    -0.43
     netto
    -0.40
    átiles
    -0.39
    idé
    -0.39
    bouw
    -0.38
    ługość
    -0.37
    ยอด
    -0.37
    Override
    -0.37
     match
    -0.36
    POSITIVE LOGITS
     ninth
    1.31
     eighth
    1.22
     seventh
    1.17
     thirteenth
    1.17
    ninth
    1.13
     twelfth
    1.11
     tenth
    1.09
     eleventh
    1.09
     fifteenth
    1.08
    seventh
    1.07
    Act Density 0.135%

    No Known Activations