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

    Neuronpedia

    INDEX
    Explanations

    words related to specific industries or sectors

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various societal and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.86
    xon
    -0.75
    ighed
    -0.73
    nw
    -0.72
    ¶ħ
    -0.67
    rehens
    -0.67
    Tro
    -0.66
    peed
    -0.66
    idium
    -0.66
    upper
    -0.66
    POSITIVE LOGITS
     topics
    0.93
     contexts
    0.93
     affairs
    0.93
     stimuli
    0.91
     situations
    0.91
     activities
    0.90
     subjects
    0.90
     societies
    0.89
     entities
    0.89
     endeavors
    0.88
    Act Density 0.402%

    No Known Activations