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

    Neuronpedia

    INDEX
    Explanations

    information about the original publication source and any reprints or reproductions

    oai_token-act-pair · gpt-3.5-turbo

    references to article publication and attribution details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.77
    Ĭ±
    -0.63
    ãĥı
    -0.62
    cases
    -0.60
     GPUs
    -0.60
     alike
    -0.59
     rooms
    -0.59
    æ©
    -0.58
     nig
    -0.58
    ¯
    -0.58
    POSITIVE LOGITS
    endum
    0.85
     POLITICO
    0.80
    terday
    0.77
    inion
    0.76
    aretz
    0.75
    isode
    0.71
     HuffPost
    0.70
    ebin
    0.70
     ILCS
    0.70
    itcher
    0.66
    Act Density 0.243%

    No Known Activations