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

    Neuronpedia

    INDEX
    Explanations

    measurements of length

    oai_token-act-pair · gpt-3.5-turbo

    measurements of distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.93
    oly
    -0.81
    amac
    -0.74
    eers
    -0.71
     Mothers
    -0.67
     entitlement
    -0.66
    analysis
    -0.65
     Plasma
    -0.63
     Byrne
    -0.62
     Spending
    -0.61
    POSITIVE LOGITS
     apiece
    0.92
    itudinal
    0.89
    hops
    0.84
     thick
    0.83
     ILCS
    0.79
     tall
    0.78
    iameter
    0.77
     diameter
    0.77
     perpendicular
    0.73
    deep
    0.73
    Act Density 0.075%

    No Known Activations