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

    Neuronpedia

    INDEX
    Explanations

    instances of cooperative action or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antro
    -0.17
    RCT
    -0.15
    adem
    -0.15
    idden
    -0.14
    ÑĮв
    -0.14
    upert
    -0.14
    ouve
    -0.14
    anske
    -0.14
    workspace
    -0.14
    wner
    -0.14
    POSITIVE LOGITS
     hand
    0.32
     side
    0.30
     closely
    0.28
     shoulder
    0.25
     alongside
    0.25
    Âłc
    0.24
     directly
    0.24
     towards
    0.23
     toward
    0.23
     closing
    0.23
    Act Density 0.033%

    No Known Activations