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

    Neuronpedia

    INDEX
    Explanations

    network-related strings like IP addresses and ports

    oai_token-act-pair · gpt-3.5-turbo

    colons and annotated data structures potentially indicating configuration settings or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jude
    -0.65
     behavi
    -0.64
     sided
    -0.63
     troubles
    -0.62
     Gulf
    -0.61
     back
    -0.60
     outright
    -0.60
     Sant
    -0.59
     Pratt
    -0.58
     whip
    -0.58
    POSITIVE LOGITS
    hover
    1.19
    memory
    0.99
    YES
    0.97
    latest
    0.96
    before
    0.89
    checked
    0.84
    eyes
    0.84
    344
    0.84
    3000
    0.83
    5000
    0.83
    Act Density 0.088%

    No Known Activations