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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turned into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yright
    -0.78
    inately
    -0.72
    warning
    -0.69
    orno
    -0.64
    anto
    -0.60
     Cran
    -0.59
     hinted
    -0.59
    erity
    -0.59
     downed
    -0.59
     undertook
    -0.58
    POSITIVE LOGITS
    ãĤ§
    0.78
    Ò
    0.74
     adulthood
    0.73
    pload
    0.65
    è¡
    0.64
    Space
    0.64
     usable
    0.63
     lifelong
    0.63
     mush
    0.63
     ashes
    0.62
    Act Density 0.039%

    No Known Activations