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

    Neuronpedia

    INDEX
    Explanations

    URL links

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bills
    -0.68
     Plants
    -0.65
     apes
    -0.65
     memos
    -0.64
     Monkey
    -0.63
    ļéĨĴ
    -0.62
     Pyramid
    -0.60
     Throne
    -0.60
     Wasserman
    -0.60
     Doodle
    -0.60
    POSITIVE LOGITS
    hm
    0.98
    gallery
    0.94
    brow
    0.88
    jon
    0.85
    handle
    0.84
    kj
    0.81
    hash
    0.81
    expl
    0.81
    j
    0.80
    jac
    0.79
    Act Density 0.014%

    No Known Activations