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

    Neuronpedia

    INDEX
    Explanations

    words related to restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.78
    ublic
    -0.77
    FORE
    -0.74
    earth
    -0.72
    GROUND
    -0.72
    itely
    -0.71
    è£
    -0.71
    Sham
    -0.70
    IRED
    -0.70
    ilon
    -0.69
    POSITIVE LOGITS
     access
    1.21
     freedoms
    1.04
     liability
    1.02
     exposure
    0.97
     allowable
    0.93
     availability
    0.91
     possibilities
    0.90
     mobility
    0.90
     permissible
    0.89
     visibility
    0.89
    Act Density 0.084%

    No Known Activations