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

    Neuronpedia

    INDEX
    Explanations

    references to containers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erty
    -0.15
    ael
    -0.15
    rap
    -0.15
    helm
    -0.15
    sed
    -0.15
    enger
    -0.15
    tec
    -0.15
    ert
    -0.14
    -ÑĤо
    -0.14
    ery
    -0.14
    POSITIVE LOGITS
    laus
    0.16
    ized
    0.15
    entai
    0.15
    untime
    0.15
    apist
    0.14
    iff
    0.14
    cheng
    0.14
    onation
    0.14
    exus
    0.13
    iffs
    0.13
    Act Density 0.020%

    No Known Activations