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

    Neuronpedia

    INDEX
    Explanations

    words related to shields or protection

    oai_token-act-pair · gpt-3.5-turbo

    the term "Shield" and its various forms related to protection or defense systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.89
     Helpful
    -0.83
    jad
    -0.76
    cause
    -0.75
    iasco
    -0.72
    pheus
    -0.72
    orie
    -0.70
    phrine
    -0.69
     Judicial
    -0.68
    ASY
    -0.67
    POSITIVE LOGITS
     shields
    0.81
    heed
    0.81
     shield
    0.81
    awei
    0.76
    igans
    0.76
    maid
    0.75
     shielded
    0.74
     absorbing
    0.74
    lain
    0.73
     piercing
    0.72
    Act Density 0.020%

    No Known Activations