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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "fraction" relating to quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sands
    -0.68
    åĤ
    -0.61
    iolet
    -0.61
    dream
    -0.59
     Brunswick
    -0.58
     Shame
    -0.58
     Charter
    -0.58
    Adv
    -0.58
    DCS
    -0.55
     Ruin
    -0.55
    POSITIVE LOGITS
    imet
    0.97
    acy
    0.90
    atical
    0.87
     thereof
    0.87
     fractions
    0.85
    acies
    0.82
    ority
    0.81
    ately
    0.80
    ate
    0.79
    atic
    0.77
    Act Density 0.007%

    No Known Activations