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

    Neuronpedia

    INDEX
    Explanations

    references to specific documents or written works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uplicates
    -0.15
    shaw
    -0.15
    Ī
    -0.15
    nám
    -0.15
    ÙĦÙĤ
    -0.14
    emax
    -0.14
    è½
    -0.14
    olum
    -0.14
    owo
    -0.14
    ullen
    -0.14
    POSITIVE LOGITS
    lesc
    0.16
    uela
    0.15
    UEL
    0.14
    amble
    0.14
    /page
    0.14
    RLF
    0.14
    riott
    0.14
    ulumi
    0.14
     Roe
    0.14
     Conce
    0.13
    Act Density 0.006%

    No Known Activations