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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "paper"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "paper" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ß
    -0.69
    tery
    -0.67
    otions
    -0.65
    fitting
    -0.65
    amping
    -0.64
     Christie
    -0.62
    inately
    -0.62
    otomy
    -0.61
    ting
    -0.61
    kw
    -0.61
    POSITIVE LOGITS
    clips
    1.01
    ILY
    0.89
    apers
    0.87
    formance
    0.82
    aper
    0.82
    clip
    0.74
    ONS
    0.70
    strip
    0.68
    enegger
    0.68
    IUM
    0.67
    Act Density 0.047%

    No Known Activations