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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals or entities being respected

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that are held in high regard or esteem

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seed
    -0.84
    plan
    -0.81
    cell
    -0.74
    ohyd
    -0.74
    ohydrate
    -0.71
    plet
    -0.70
     concoct
    -0.68
    dream
    -0.67
    thur
    -0.67
    adra
    -0.66
    POSITIVE LOGITS
     respected
    0.85
    respected
    0.83
    ¿½
    0.80
    FUL
    0.73
    @@
    0.72
    SourceFile
    0.72
    ledged
    0.71
     citiz
    0.71
     peers
    0.70
    ¡
    0.68
    Act Density 0.021%

    No Known Activations