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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or impossibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emet
    -0.16
    enet
    -0.15
    bakan
    -0.15
    ÑĤим
    -0.15
    opot
    -0.14
    enance
    -0.14
     Newsp
    -0.14
    enza
    -0.13
    кеÑĤ
    -0.13
    ynam
    -0.13
    POSITIVE LOGITS
    oser
    0.15
    275
    0.15
    erif
    0.15
    769
    0.15
    icie
    0.14
    icari
    0.14
    ltr
    0.14
     anyone
    0.14
    맨
    0.14
    403
    0.13
    Act Density 0.030%

    No Known Activations