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

    Neuronpedia

    INDEX
    Explanations

    specific nouns related to abstract concepts or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts or entities that involve formal agreements or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sling
    -0.68
     Plate
    -0.66
     Cure
    -0.63
     Tau
    -0.62
     Launch
    -0.61
    Scan
    -0.60
     Moose
    -0.58
     Shuttle
    -0.57
     Lounge
    -0.57
     shuttle
    -0.56
    POSITIVE LOGITS
     existed
    1.00
     exists
    0.94
     exist
    0.88
    manship
    0.80
    idious
    0.80
    SHIP
    0.78
    hip
    0.75
    ials
    0.68
    roman
    0.68
    ologies
    0.67
    Act Density 0.139%

    No Known Activations