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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate joint activities or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergies
    -0.80
     Diſ
    -0.64
    ModelSerializer
    -0.62
    readFileSync
    -0.62
     TDI
    -0.59
    eer
    -0.59
    μως
    -0.59
     spira
    -0.58
     personaggio
    -0.58
    orphism
    -0.57
    POSITIVE LOGITS
     joint
    1.72
     Joint
    1.68
    Joint
    1.64
     JOINT
    1.64
    joint
    1.63
    JOINT
    1.48
     Joints
    1.44
     jointly
    1.35
     joints
    1.32
    joints
    1.25
    Act Density 0.133%

    No Known Activations