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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numeric values or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itely
    -0.76
    omy
    -0.72
     arsen
    -0.72
    agan
    -0.72
    avis
    -0.69
    ancing
    -0.68
    icka
    -0.67
     enticing
    -0.67
    anced
    -0.66
     photoc
    -0.65
    POSITIVE LOGITS
    mAh
    1.27
    Hz
    0.94
    rpm
    0.94
    mA
    0.92
     MHz
    0.91
     Hz
    0.90
    MHz
    0.89
     rpm
    0.86
    px
    0.85
     kcal
    0.81
    Act Density 0.077%

    No Known Activations