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

    Neuronpedia

    INDEX
    Explanations

    URLs or website addresses in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to websites and online platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.81
    LET
    -0.70
    Synopsis
    -0.65
    ENGTH
    -0.64
    FN
    -0.63
    Leader
    -0.63
     Helsinki
    -0.61
    Finish
    -0.61
    FUL
    -0.60
    Honest
    -0.60
    POSITIVE LOGITS
    chool
    1.10
    afety
    1.07
    earch
    1.05
    uggest
    1.02
    paces
    1.01
    erv
    1.01
    etter
    0.99
    hops
    0.98
    omal
    0.97
    ometimes
    0.96
    Act Density 0.047%

    No Known Activations