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

    Neuronpedia

    INDEX
    Explanations

    phrases instructing to "get" something

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.61
     defe
    -0.61
    pled
    -0.59
     experiment
    -0.58
    pard
    -0.57
     evoke
    -0.56
    è¦ļéĨĴ
    -0.56
     taboo
    -0.54
     portray
    -0.54
    bery
    -0.54
    POSITIVE LOGITS
     rid
    1.16
    TING
    1.10
    cloneembedreportprint
    0.93
    away
    0.92
    aways
    0.83
    ãĥ³ãĤ¸
    0.77
    ters
    0.77
     Rid
    0.75
    zl
    0.73
     Away
    0.73
    Act Density 0.039%

    No Known Activations