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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases using "might as well" or "could just as easily"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roads
    -0.63
    arial
    -0.61
    tsky
    -0.61
    oresc
    -0.59
     briefs
    -0.59
    lining
    -0.58
     Reporting
    -0.56
    allery
    -0.55
     Madagascar
    -0.55
    acent
    -0.55
    POSITIVE LOGITS
     well
    1.32
    well
    1.16
    phy
    0.89
     easily
    0.88
    ym
    0.83
    semble
    0.83
     Well
    0.82
    Well
    0.81
     plaus
    0.79
    ynchron
    0.78
    Act Density 0.034%

    No Known Activations