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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eric
    -0.96
    issance
    -0.90
    yss
    -0.86
    naire
    -0.83
    erers
    -0.78
    erer
    -0.77
    nant
    -0.75
    nai
    -0.75
    estine
    -0.74
    fred
    -0.74
    POSITIVE LOGITS
     precautions
    0.98
     hazards
    0.96
     net
    0.92
     hazard
    0.91
     valve
    0.89
     nets
    0.87
     valves
    0.83
     precaution
    0.83
     margins
    0.79
     margin
    0.76
    Act Density 0.045%

    No Known Activations