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

    Neuronpedia

    INDEX
    Explanations

    references to "these" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neh
    -0.15
    lek
    -0.15
    emon
    -0.15
    oke
    -0.14
    osis
    -0.14
    ollapsed
    -0.14
    otypes
    -0.13
    uted
    -0.13
    odal
    -0.13
    upal
    -0.13
    POSITIVE LOGITS
    oret
    0.22
    eyin
    0.15
     EÅŁ
    0.15
    iscard
    0.14
    enha
    0.13
    rvine
    0.13
    LOAT
    0.13
    gend
    0.13
    esimal
    0.13
    gL
    0.13
    Act Density 0.052%

    No Known Activations