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

    Neuronpedia

    INDEX
    Explanations

    expressions of customer satisfaction and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.15
     nossa
    -0.15
     vår
    -0.14
    ruk
    -0.14
     wir
    -0.14
     ons
    -0.14
     us
    -0.14
     наÑĪиÑħ
    -0.14
     our
    -0.13
     unseren
    -0.13
    POSITIVE LOGITS
     We
    0.87
    WE
    0.82
    -we
    0.78
     WE
    0.77
    We
    0.77
    _we
    0.74
    we
    0.72
     Weiss
    0.62
    _WE
    0.62
    /we
    0.60
    Act Density 0.401%

    No Known Activations