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

    Neuronpedia

    INDEX
    Explanations

    similes comparing different situations

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.92
    iencies
    -0.89
    idates
    -0.82
    iets
    -0.77
    icators
    -0.77
    icator
    -0.73
    icity
    -0.72
    icals
    -0.69
    ixel
    -0.69
    odes
    -0.68
    POSITIVE LOGITS
    lier
    1.34
    liest
    1.25
    lihood
    1.01
     comparing
    0.81
     wildfire
    0.79
     waking
    0.78
     watching
    0.75
    liness
    0.75
     spitting
    0.74
     unto
    0.72
    Act Density 0.070%

    No Known Activations