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

    Neuronpedia

    INDEX
    Explanations

    words related to the polar regions or polarizing topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to polarity and polar concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ECH
    -0.81
    CHA
    -0.79
    riad
    -0.78
    ptroller
    -0.78
    esis
    -0.75
    enance
    -0.75
    INA
    -0.74
    roma
    -0.74
    ITNESS
    -0.74
    lished
    -0.73
    POSITIVE LOGITS
     polar
    0.97
     vortex
    0.88
    izing
    0.86
     oppos
    0.86
     Polar
    0.81
    itary
    0.80
     Poles
    0.79
     extremes
    0.79
    igr
    0.77
     bear
    0.77
    Act Density 0.015%

    No Known Activations