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

    Neuronpedia

    INDEX
    Explanations

    references to publications and related sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.17
    mtree
    -0.16
    ives
    -0.15
    Ú©ÛĮÙĦ
    -0.15
    ive
    -0.15
    tü
    -0.15
    zÅij
    -0.15
    ä»ģ
    -0.14
     HIP
    -0.14
    ptic
    -0.14
    POSITIVE LOGITS
    (crate
    0.21
    lix
    0.21
    lique
    0.19
    /pub
    0.19
    bing
    0.18
    jabi
    0.18
    bert
    0.18
    lius
    0.17
    erculosis
    0.17
    ertino
    0.16
    Act Density 0.012%

    No Known Activations