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

    Neuronpedia

    INDEX
    Explanations

    words related to location, including specific places and directions

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [+
    -0.88
    ?]
    -0.75
     tho
    -0.74
     XD
    -0.74
     [/
    -0.73
     Secondly
    -0.69
    Therefore
    -0.67
     afore
    -0.67
     =>
    -0.67
    ]"
    -0.67
    POSITIVE LOGITS
     unmist
    1.12
     strikingly
    0.96
     decidedly
    0.93
     breathtaking
    0.87
     conspic
    0.87
     startling
    0.87
     undeniably
    0.87
     vividly
    0.86
     remarkably
    0.86
     unrem
    0.84
    Act Density 0.894%

    No Known Activations