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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or contrasts using the word "least"

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "at least."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shr
    -0.75
    taboola
    -0.74
     FANT
    -0.71
    mage
    -0.68
    ander
    -0.67
    ãĥ¼ãĤ¯
    -0.67
    sl
    -0.65
    GBT
    -0.65
    cum
    -0.63
    osc
    -0.63
    POSITIVE LOGITS
    nob
    0.65
     Nin
    0.65
     Teresa
    0.63
     partly
    0.62
    een
    0.61
     Eleven
    0.60
     Seems
    0.60
     Theresa
    0.60
    onse
    0.59
     squares
    0.59
    Act Density 0.019%

    No Known Activations