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

    Neuronpedia

    INDEX
    Explanations

    references to hacking and hacks

    oai_token-act-pair · gpt-3.5-turbo

    references related to hacking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    eele
    -0.65
    obe
    -0.64
    ikk
    -0.64
     Veter
    -0.64
    oplan
    -0.63
     Presbyter
    -0.62
     Leban
    -0.62
    wait
    -0.62
    oran
    -0.61
    POSITIVE LOGITS
    intosh
    1.38
    aday
    0.96
    lar
    0.85
    athon
    0.80
    driver
    0.79
    netic
    0.79
    RF
    0.79
    romising
    0.75
    hent
    0.75
    paces
    0.74
    Act Density 0.047%

    No Known Activations