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

    Neuronpedia

    INDEX
    Explanations

    mentions of koalas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umer
    -0.18
    ixon
    -0.18
    o
    -0.17
    uously
    -0.16
    eon
    -0.15
    uer
    -0.15
    è·¡
    -0.15
    enger
    -0.15
    herits
    -0.15
    bil
    -0.15
    POSITIVE LOGITS
    ehler
    0.23
    ala
    0.22
    pec
    0.18
    resh
    0.17
    erner
    0.16
    za
    0.16
    atrice
    0.16
    hip
    0.16
    lund
    0.15
    ALA
    0.15
    Act Density 0.013%

    No Known Activations