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

    Neuronpedia

    INDEX
    Explanations

    fractions or parts of a whole

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fraction" and its related numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sands
    -0.72
    Adv
    -0.67
    Recommend
    -0.67
     Brunswick
    -0.65
    Draft
    -0.60
    raid
    -0.60
    ordes
    -0.59
     recommendations
    -0.59
     Shame
    -0.59
    Guard
    -0.59
    POSITIVE LOGITS
     thereof
    0.92
    ority
    0.91
     fractions
    0.88
    acy
    0.85
    imet
    0.85
    eworks
    0.83
    acies
    0.79
    atical
    0.79
     ILCS
    0.76
    ancial
    0.76
    Act Density 0.014%

    No Known Activations