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

    Neuronpedia

    INDEX
    Explanations

    text related to political consultations, commitments, and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate formatting or coding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accomp
    -0.63
     Imper
    -0.62
     mash
    -0.62
     encount
    -0.59
     crus
    -0.58
     wors
    -0.57
     denomin
    -0.56
     magn
    -0.56
     Trojan
    -0.56
     backdrop
    -0.56
    POSITIVE LOGITS
    him
    1.20
    them
    1.10
    their
    1.04
    his
    0.95
    selves
    0.94
    gently
    0.92
    onto
    0.92
    DERR
    0.89
    your
    0.85
    ationally
    0.85
    Act Density 0.312%

    No Known Activations