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

    Neuronpedia

    INDEX
    Explanations

    colors mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of coordination in complex phrases or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administ
    -0.74
    SHIP
    -0.74
    iets
    -0.72
    Report
    -0.70
    amily
    -0.69
    udence
    -0.68
    makers
    -0.68
    itant
    -0.68
    hesda
    -0.67
    Reviewer
    -0.66
    POSITIVE LOGITS
     striped
    1.12
     yellow
    1.11
     grey
    1.09
     orange
    1.08
     purple
    1.07
     gray
    1.06
     blue
    0.99
     green
    0.95
     violet
    0.95
    yellow
    0.92
    Act Density 0.150%

    No Known Activations