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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating commonalities or similarities between entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in common."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilst
    -0.69
    hov
    -0.66
    lynn
    -0.63
     brim
    -0.61
    ocard
    -0.59
    gart
    -0.59
    wash
    -0.59
    gans
    -0.57
    killed
    -0.57
    ALSE
    -0.57
    POSITIVE LOGITS
    clusions
    1.05
    eff
    0.93
    effic
    0.92
     terms
    0.90
    terms
    0.85
     common
    0.84
     abundance
    0.82
     hindsight
    0.80
     regards
    0.80
    between
    0.80
    Act Density 0.164%

    No Known Activations