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

    Neuronpedia

    INDEX
    Explanations

    numbers and technical details related to various subjects

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.86
    ei
    -0.86
    yang
    -0.83
    ey
    -0.77
    phis
    -0.75
    hner
    -0.75
    pressure
    -0.74
    geist
    -0.73
    pty
    -0.72
    gie
    -0.71
    POSITIVE LOGITS
     ILCS
    1.37
    ERSON
    0.79
    ISH
    0.75
    %:
    0.74
    ishing
    0.74
    ovember
    0.70
    ENCY
    0.70
    çļ
    0.70
    ances
    0.69
    678
    0.68
    Act Density 0.060%

    No Known Activations