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

    Neuronpedia

    INDEX
    Explanations

    occurrences of social interactions and communal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruptions
    -0.15
     sokak
    -0.15
    Toast
    -0.15
     actionTypes
    -0.14
     bureaucr
    -0.14
     Boiler
    -0.14
    unan
    -0.14
    Cheers
    -0.14
    ijken
    -0.14
    forces
    -0.13
    POSITIVE LOGITS
     books
    0.22
     paper
    0.21
     supplies
    0.20
     materials
    0.20
     papers
    0.20
     masking
    0.20
     umb
    0.20
     masks
    0.19
     implements
    0.19
     chairs
    0.19
    Act Density 0.881%

    No Known Activations