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

    Neuronpedia

    INDEX
    Explanations

    references to safety measures or concerns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of safety and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.93
    eric
    -0.88
    yss
    -0.83
    naire
    -0.82
    ette
    -0.81
    estine
    -0.77
    iguous
    -0.76
    eta
    -0.76
    ement
    -0.75
    nai
    -0.75
    POSITIVE LOGITS
     precautions
    0.84
     hazards
    0.83
     net
    0.80
     valve
    0.78
     safety
    0.78
     hazard
    0.76
     practition
    0.74
     valves
    0.72
    safety
    0.72
     violations
    0.71
    Act Density 0.055%

    No Known Activations