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

    Neuronpedia

    INDEX
    Explanations

    phrases related to putting things together or organizing aspects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to assembling or combining elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assadors
    -0.76
    OPA
    -0.75
    ranged
    -0.74
    SPONSORED
    -0.74
    facing
    -0.72
    asia
    -0.71
    dinand
    -0.71
    olphin
    -0.70
    ilyn
    -0.70
    rection
    -0.70
    POSITIVE LOGITS
     edges
    1.05
     folds
    0.98
     strands
    0.94
     seams
    0.94
     corners
    0.91
     layers
    0.90
     knots
    0.90
     weeds
    0.90
     fragments
    0.89
     feathers
    0.88
    Act Density 0.383%

    No Known Activations