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

    Neuronpedia

    INDEX
    Explanations

    terms related to cooperation and cooperative activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    space
    -0.18
    gie
    -0.18
    spe
    -0.16
     cooperating
    -0.15
     cooperative
    -0.15
    itesse
    -0.15
    gew
    -0.15
    -0.15
     còn
    -0.15
    Coeff
    -0.14
    POSITIVE LOGITS
    mans
    0.20
    atives
    0.18
    stown
    0.18
    ating
    0.17
    atively
    0.17
    ider
    0.17
    ativa
    0.17
    portunity
    0.17
    atings
    0.17
    esh
    0.17
    Act Density 0.011%

    No Known Activations