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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of a protective barrier or defense mechanism

    oai_token-act-pair · gpt-3.5-turbo

    references to protective barriers or defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PM
    -0.80
    cause
    -0.72
    OTAL
    -0.70
     Helpful
    -0.69
    gres
    -0.68
    eph
    -0.67
    uria
    -0.67
     Judicial
    -0.66
    ETA
    -0.66
    orie
    -0.64
    POSITIVE LOGITS
     shield
    1.13
     shields
    1.10
     shielding
    0.94
    maid
    0.83
     maiden
    0.82
    heed
    0.82
    buster
    0.80
     curtain
    0.78
     shielded
    0.77
    igans
    0.77
    Act Density 0.006%

    No Known Activations