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

    Neuronpedia

    INDEX
    Explanations

    words related to shields

    oai_token-act-pair · gpt-3.5-turbo

    references to "shields" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.85
    jad
    -0.76
    cause
    -0.75
     âĸº
    -0.75
     Helpful
    -0.75
    orie
    -0.72
    ovie
    -0.71
    iasco
    -0.71
    pheus
    -0.70
    zzy
    -0.69
    POSITIVE LOGITS
    heed
    0.87
     shield
    0.77
     shields
    0.76
    lain
    0.73
     absorbing
    0.72
     shielded
    0.71
    maid
    0.70
     piercing
    0.70
    igans
    0.69
     maiden
    0.68
    Act Density 0.026%

    No Known Activations