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

    Neuronpedia

    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -0.89
    stad
    -0.80
    screen
    -0.77
    kaya
    -0.77
    spring
    -0.75
    uration
    -0.75
    tery
    -0.74
    ions
    -0.74
    lasses
    -0.74
    er
    -0.73
    POSITIVE LOGITS
     Kitt
    0.77
     hitch
    0.70
    ³³³³
    0.70
    Downloadha
    0.69
     Chrys
    0.68
    NetMessage
    0.67
    obyl
    0.66
     Skydragon
    0.64
     Dome
    0.64
    irens
    0.63
    Act Density 0.050%

    No Known Activations