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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety and security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fred
    -0.82
    frey
    -0.81
    essee
    -0.78
    eric
    -0.75
    attr
    -0.75
    hun
    -0.72
    pel
    -0.70
    ette
    -0.68
    eds
    -0.68
    ional
    -0.65
    POSITIVE LOGITS
     safer
    1.03
     safest
    1.02
     safe
    0.92
    saf
    0.86
     redes
    0.79
     endanger
    0.78
     havens
    0.78
     alternatives
    0.77
    ashtra
    0.76
     safety
    0.74
    Act Density 0.006%

    No Known Activations