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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "world."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imon
    -0.86
    veyard
    -0.85
    ippi
    -0.82
     actionGroup
    -0.78
    merce
    -0.75
    ussen
    -0.74
    oug
    -0.72
    Corp
    -0.71
    odox
    -0.71
    uctor
    -0.68
    POSITIVE LOGITS
    liness
    0.83
    building
    0.83
     premiere
    0.81
    wide
    0.78
     Famous
    0.71
     championships
    0.70
    scape
    0.69
     economy
    0.69
     Wide
    0.68
     wide
    0.68
    Act Density 0.051%

    No Known Activations