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

    Neuronpedia

    INDEX
    Explanations

    proper names related to public figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Diana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oos
    -0.78
    doors
    -0.77
    heimer
    -0.74
    oop
    -0.73
    fits
    -0.72
    oops
    -0.72
    ten
    -0.70
    heastern
    -0.69
    ears
    -0.69
    thren
    -0.68
    POSITIVE LOGITS
     Diana
    1.17
     Wynne
    0.84
    ILY
    0.79
    racuse
    0.75
     Gab
    0.75
     Kali
    0.73
     Sachs
    0.73
     sacrific
    0.71
     Yor
    0.71
     eclipse
    0.69
    Act Density 0.025%

    No Known Activations