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

    Neuronpedia

    INDEX
    Explanations

    statements introducing arguments or someone presenting a point of view

    oai_token-act-pair · gpt-3.5-turbo

    statements or claims made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stand
    -0.71
     mean
    -0.68
     happen
    -0.66
     supposed
    -0.64
     sound
    -0.62
     clear
    -0.62
     dotted
    -0.62
     necessary
    -0.61
     present
    -0.61
     appropriate
    -0.59
    POSITIVE LOGITS
     argues
    2.20
     warns
    2.12
     concedes
    2.12
     acknowledges
    2.09
     contends
    2.09
     insists
    2.08
     accuses
    2.07
     asks
    2.05
     admits
    2.05
     blames
    2.05
    Act Density 0.071%

    No Known Activations