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

    Neuronpedia

    INDEX
    Explanations

    instances of objects being manipulated or arranged

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :
    -0.16
    ,
    -0.16
     clockwise
    -0.16
     Around
    -0.16
    round
    -0.16
    ↵
    -0.15
     around
    -0.15
     gross
    -0.15
     inward
    -0.15
    tm
    -0.15
    POSITIVE LOGITS
     suspended
    0.26
     unsupported
    0.23
    Supported
    0.22
    supported
    0.22
    uspended
    0.21
     suspend
    0.21
    flush
    0.20
    unsupported
    0.20
     supported
    0.20
     stationary
    0.20
    Act Density 0.207%

    No Known Activations