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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts in sentences

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate contrast or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.75
    hig
    -0.73
     exting
    -0.73
    bas
    -0.71
    SPONSORED
    -0.71
    orthy
    -0.71
     predec
    -0.70
    pez
    -0.70
    atl
    -0.68
    Rated
    -0.68
    POSITIVE LOGITS
     we
    0.80
     they
    0.72
     acknowledging
    0.71
     spirits
    0.68
    fy
    0.68
     it
    0.67
     SOME
    0.67
     you
    0.66
     there
    0.66
     he
    0.63
    Act Density 0.134%

    No Known Activations