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

    Neuronpedia

    INDEX
    Explanations

    mentions of universities, debates, and academic discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.86
    hower
    -0.75
    glers
    -0.70
    ptive
    -0.69
    mits
    -0.67
    hyde
    -0.67
    hound
    -0.66
    dylib
    -0.64
    pas
    -0.63
    metry
    -0.63
    POSITIVE LOGITS
    REAM
    1.30
    UFF
    1.15
    OCK
    1.13
    DERR
    1.13
    AGE
    1.11
    RE
    1.05
    ALK
    1.03
    ACK
    1.00
    AY
    0.99
    alker
    0.98
    Act Density 0.014%

    No Known Activations