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

    Neuronpedia

    INDEX
    Explanations

    computer-related information such as passwords, usernames, and program commands

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    letter
    -0.76
     Angel
    -0.72
     Dion
    -0.72
    bon
    -0.70
     Lav
    -0.69
     Levin
    -0.69
     RAD
    -0.69
     Angle
    -0.69
    hyp
    -0.67
    Ark
    -0.67
    POSITIVE LOGITS
    gow
    0.99
    ico
    0.97
    owa
    0.93
     (£
    0.88
    ich
    0.86
    itely
    0.84
    ffield
    0.84
    gew
    0.83
    ively
    0.83
    ega
    0.81
    Act Density 0.374%

    No Known Activations