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

    Neuronpedia

    INDEX
    Explanations

    source code-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and source materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACP
    -0.81
    FACE
    -0.79
    DAY
    -0.76
    Ń·
    -0.73
    TAG
    -0.73
    ington
    -0.71
    Interstitial
    -0.70
    Switch
    -0.68
    achine
    -0.68
    Skip
    -0.67
    POSITIVE LOGITS
     whence
    0.74
    ortium
    0.73
    ucl
    0.73
     ISI
    0.70
     Riy
    0.68
     wealth
    0.68
     archives
    0.67
    jiang
    0.67
     archive
    0.66
     Medline
    0.66
    Act Density 0.258%

    No Known Activations