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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities being highly esteemed or admired

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "respected"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seed
    -0.81
    adra
    -0.76
    plan
    -0.76
    ggle
    -0.75
    gger
    -0.74
    plet
    -0.74
    opter
    -0.73
    thur
    -0.73
     Jackets
    -0.71
    strip
    -0.71
    POSITIVE LOGITS
     respected
    0.99
    respected
    0.84
    FUL
    0.75
     Seym
    0.73
     peers
    0.72
     ambassadors
    0.71
     bast
    0.70
     citiz
    0.69
     colleagues
    0.68
     media
    0.67
    Act Density 0.012%

    No Known Activations