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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and emergency procedures or equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to specific concepts or terms associated with safety and protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.76
    hibition
    -0.75
    ventory
    -0.74
    vin
    -0.74
    ces
    -0.73
    VALUE
    -0.71
    avez
    -0.71
    apolis
    -0.70
    uate
    -0.69
    Residents
    -0.69
    POSITIVE LOGITS
     raft
    1.02
    andowski
    0.82
    ieri
    0.81
    ing
    0.77
    s
    0.77
    aroo
    0.76
    éĹĺ
    0.70
    undle
    0.69
    itudinal
    0.69
    ingen
    0.67
    Act Density 0.010%

    No Known Activations