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

    Neuronpedia

    INDEX
    Explanations

    computer-related terms and actions such as downloading documents and running scripts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of documents and files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iage
    -0.65
    Thompson
    -0.61
    CLASS
    -0.60
    ALLY
    -0.58
    rick
    -0.56
    los
    -0.55
    mn
    -0.54
    OUS
    -0.54
     fringe
    -0.53
    atever
    -0.53
    POSITIVE LOGITS
     themselves
    1.10
    '
    1.09
    ystem
    1.00
    hip
    0.98
    mith
    0.97
    cape
    0.95
    pace
    0.92
    hare
    0.91
    etting
    0.90
    heet
    0.89
    Act Density 0.462%

    No Known Activations