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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "least"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use the expression "at least."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.72
    hou
    -0.70
     FANT
    -0.67
    icides
    -0.63
    iday
    -0.62
    IDES
    -0.62
    ãĤ¿
    -0.59
    hr
    -0.56
    bern
    -0.56
     phyl
    -0.55
    POSITIVE LOGITS
     partly
    0.83
     partially
    0.80
    foundland
    0.74
     temporarily
    0.74
    etheless
    0.71
     oct
    0.70
     indirectly
    0.69
    onse
    0.67
     rhet
    0.66
     theoretically
    0.66
    Act Density 0.018%

    No Known Activations