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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a similarity or comparison to something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "something like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Published
    -0.75
    Ô
    -0.72
    aii
    -0.68
    Americ
    -0.68
    gins
    -0.67
    OG
    -0.65
    Bow
    -0.64
    ³³³³
    -0.63
    Versions
    -0.63
    Limited
    -0.63
    POSITIVE LOGITS
    lihood
    1.03
    lier
    0.74
    adish
    0.66
    peror
    0.60
    anism
    0.60
     hers
    0.60
     happen
    0.59
     Rowling
    0.58
     Sue
    0.58
     replicate
    0.56
    Act Density 0.054%

    No Known Activations