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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety

    oai_token-act-pair · gpt-3.5-turbo

    references to safety and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.95
    eric
    -0.86
    naire
    -0.83
    ement
    -0.80
    ette
    -0.79
    yss
    -0.77
    eta
    -0.75
    sonian
    -0.75
    iguous
    -0.72
    ional
    -0.72
    POSITIVE LOGITS
     safety
    0.84
     hazards
    0.83
     practition
    0.78
     margins
    0.78
    ailability
    0.77
     net
    0.76
     precautions
    0.74
     valve
    0.74
     hazard
    0.73
     margin
    0.72
    Act Density 0.039%

    No Known Activations