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

    Neuronpedia

    INDEX
    Explanations

    concepts related to measurement and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Olson
    -0.17
    istrovstvÃŃ
    -0.16
    avir
    -0.16
    ç
    -0.16
    vir
    -0.14
     Geh
    -0.13
    è°±
    -0.13
    ariate
    -0.13
    太éĥİ
    -0.13
    .string
    -0.13
    POSITIVE LOGITS
    enna
    0.18
    ammed
    0.16
    enu
    0.15
    945
    0.15
    yonel
    0.15
    ặn
    0.14
    oyer
    0.14
    hud
    0.14
    ammad
    0.14
    ocket
    0.14
    Act Density 0.063%

    No Known Activations