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

    Neuronpedia

    INDEX
    Explanations

    descriptions of scenes in an urban setting

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uly
    -0.82
    thal
    -0.75
     previously
    -0.73
     defe
    -0.70
    iber
    -0.67
     dimensional
    -0.67
     hostage
    -0.65
     tyr
    -0.65
     exclusively
    -0.64
     initially
    -0.64
    POSITIVE LOGITS
     Occasionally
    1.13
     Visitors
    1.10
     Amid
    1.06
     Residents
    1.05
     Each
    1.04
     Others
    1.04
     Meanwhile
    1.04
     Worse
    1.03
     But
    1.03
    toggle
    1.03
    Act Density 0.793%

    No Known Activations