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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to power, measurements, and financial amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.74
    hunt
    -0.74
    tern
    -0.74
    ched
    -0.72
    par
    -0.69
    bear
    -0.68
    abol
    -0.67
    Fram
    -0.66
    glas
    -0.64
    nam
    -0.64
    POSITIVE LOGITS
     ILCS
    0.87
    inyl
    0.79
    orsi
    0.77
     MHz
    0.76
    s
    0.75
    Hz
    0.73
    isse
    0.72
     degrees
    0.72
    ault
    0.71
     volts
    0.71
    Act Density 0.045%

    No Known Activations