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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing desires or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compass
    -0.87
    grounds
    -0.87
    soDeliveryDate
    -0.76
    herer
    -0.73
    hooting
    -0.70
    Kings
    -0.68
    wise
    -0.67
    LAN
    -0.66
    geist
    -0.66
    Offline
    -0.65
    POSITIVE LOGITS
     anymore
    1.06
     bother
    0.97
     necessarily
    0.94
     interfere
    0.94
     spoil
    0.93
     celebrate
    0.92
     participate
    0.91
     disturb
    0.89
     compete
    0.89
     indulge
    0.89
    Act Density 0.079%

    No Known Activations