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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desires or intentions of action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating desires and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPS
    -0.71
    written
    -0.67
    edient
    -0.67
     Cosponsors
    -0.65
     Lines
    -0.65
     Thumbnails
    -0.64
    soDeliveryDate
    -0.62
    padding
    -0.61
     awaiting
    -0.61
    Guest
    -0.60
    POSITIVE LOGITS
     succeed
    0.95
     survive
    0.94
     truly
    0.81
     gain
    0.80
     congr
    0.77
     legitimately
    0.77
     achieve
    0.74
     celebrate
    0.74
     compete
    0.73
     pursue
    0.73
    Act Density 0.096%

    No Known Activations