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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical documentation or programming

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALD
    -0.78
     Haku
    -0.77
    ahl
    -0.73
    в
    -0.72
    ãĤ¤
    -0.69
    EY
    -0.68
    ãĢIJ
    -0.67
    Īè
    -0.67
     Alchemist
    -0.66
    alys
    -0.66
    POSITIVE LOGITS
    p
    1.34
    P
    1.11
    Ps
    1.11
    ps
    1.10
    pg
    1.07
    pie
    1.05
    pee
    1.04
    pa
    1.04
    pu
    1.04
    pod
    1.02
    Act Density 0.212%

    No Known Activations