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

    Neuronpedia

    INDEX
    Explanations

    phrases or words with the sequence of characters "x"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the letter 'x'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.77
    assetsadobe
    -0.76
     Courage
    -0.71
    £ı
    -0.71
    milo
    -0.69
    sburgh
    -0.69
     destro
    -0.68
     cannabin
    -0.67
     kinderg
    -0.67
     convol
    -0.67
    POSITIVE LOGITS
    imity
    1.13
    posure
    1.10
    odus
    1.10
    avier
    1.09
    actly
    1.09
    press
    1.08
    posed
    1.07
    cellence
    1.06
    aminer
    1.06
    ample
    0.98
    Act Density 0.026%

    No Known Activations