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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    single-letter or short names that likely refer to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wide
    -0.73
     Driving
    -0.67
     Wide
    -0.65
     projector
    -0.65
     ****
    -0.64
     fluorescent
    -0.63
     ��������
    -0.62
     1600
    -0.62
     ***
    -0.62
     DISTRICT
    -0.61
    POSITIVE LOGITS
    ipp
    0.96
    utter
    0.89
    lem
    0.88
    ourn
    0.87
    aren
    0.87
    essel
    0.85
    airo
    0.84
    isner
    0.84
    ubb
    0.84
    iller
    0.84
    Act Density 0.183%

    No Known Activations