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

    Neuronpedia

    INDEX
    Explanations

    expressions involving multiplication or increase, often with the term "fold"

    oai_token-act-pair · gpt-3.5-turbo

    references to multiplicative concepts or repetitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assetsadobe
    -0.71
    IRO
    -0.69
    FTWARE
    -0.69
    BAT
    -0.69
    nesota
    -0.69
    ulia
    -0.68
    igslist
    -0.68
    usalem
    -0.67
    Dialogue
    -0.67
    acea
    -0.66
    POSITIVE LOGITS
    fold
    1.20
    ername
    0.89
     fold
    0.88
    ers
    0.85
    edly
    0.74
    clip
    0.73
    cation
    0.72
    cause
    0.71
    theless
    0.71
    forward
    0.70
    Act Density 0.012%

    No Known Activations