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

    Neuronpedia

    INDEX
    Explanations

    command-related instructions or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    commands related to setting configurations or parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.80
     Souls
    -0.70
    sylvania
    -0.67
     Schwe
    -0.67
    çī
    -0.66
    ä¼
    -0.66
    PH
    -0.65
    059
    -0.65
    ç«
    -0.65
    past
    -0.63
    POSITIVE LOGITS
    tle
    0.94
    ter
    0.90
    ters
    0.86
    env
    0.85
    tering
    0.85
    uid
    0.84
     forth
    0.81
    Timeout
    0.80
    cookie
    0.75
    TING
    0.74
    Act Density 0.033%

    No Known Activations