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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions or discussions about specific traits or characteristics, especially in technical or academic contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "trait"

    oai_token-act-pair · gpt-4-turbo

    references to personality traits and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Copenhagen
    -0.73
    ©¶æ
    -0.72
     Wonderland
    -0.69
     Lank
    -0.69
     Coffin
    -0.69
    cision
    -0.68
    aii
    -0.68
     GEAR
    -0.67
    NAS
    -0.65
    ñ
    -0.65
    POSITIVE LOGITS
     traits
    1.16
     trait
    1.16
    rait
    0.92
    eatures
    0.91
    ively
    0.84
     behaviours
    0.83
     predis
    0.79
     guiActiveUn
    0.78
    ilial
    0.77
    hered
    0.77
    Act Density 0.011%

    No Known Activations