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

    Neuronpedia

    INDEX
    Explanations

    explicit invitations or permissions for specific actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage feedback and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.74
    quickShipAvailable
    -0.73
    hur
    -0.69
    Cost
    -0.69
     Vish
    -0.68
    hes
    -0.68
    ritical
    -0.67
    ccording
    -0.67
     signifies
    -0.66
    lines
    -0.65
    POSITIVE LOGITS
     indulge
    1.04
     explore
    0.97
     share
    0.94
     pursue
    0.93
     speculate
    0.89
     take
    0.87
     talk
    0.86
     reproduce
    0.85
     roam
    0.85
     revisit
    0.84
    Act Density 0.099%

    No Known Activations