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

    Neuronpedia

    INDEX
    Explanations

    numbers representing percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical ranges associated with income levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.77
    agan
    -0.71
    anced
    -0.71
    verend
    -0.70
    abol
    -0.68
     symmetry
    -0.67
    ancing
    -0.66
    swick
    -0.65
    arial
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     MHz
    1.02
    px
    0.93
    MHz
    0.93
    Hz
    0.88
    +
    0.87
     meters
    0.85
    mAh
    0.85
     metres
    0.85
    +.
    0.84
     Mile
    0.82
    Act Density 0.074%

    No Known Activations