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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating permission or invitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express freedom or permission to act

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.78
    soDeliveryDate
    -0.73
    need
    -0.70
    hur
    -0.69
     millenn
    -0.68
    Roy
    -0.67
    ccording
    -0.67
    UF
    -0.65
    tons
    -0.65
    IJ
    -0.64
    POSITIVE LOGITS
     roam
    1.18
     explore
    1.06
     speculate
    0.99
     indulge
    0.97
     pursue
    0.90
     wander
    0.89
     choose
    0.88
     negotiate
    0.85
     express
    0.84
     freely
    0.83
    Act Density 0.126%

    No Known Activations