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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or procedural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    `.
    -0.86
    *.
    -0.67
    ãĥ´ãĤ¡
    -0.65
    $.
    -0.64
    !.
    -0.62
    ̶
    -0.61
     '.
    -0.60
    %.
    -0.60
    orporated
    -0.60
    \",
    -0.58
    POSITIVE LOGITS
     depends
    1.24
     varies
    1.21
     differed
    1.17
     is
    1.16
     differs
    1.16
     exceeds
    1.14
     constitutes
    1.10
     involves
    1.09
     depended
    1.08
     entails
    1.07
    Act Density 0.962%

    No Known Activations