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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future plans or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.64
     Hasan
    -0.64
     Sons
    -0.63
     surges
    -0.63
     HAS
    -0.61
    nexus
    -0.59
     respects
    -0.57
     AMA
    -0.56
     APR
    -0.55
     deteriorated
    -0.54
    POSITIVE LOGITS
     contend
    1.14
     choose
    1.05
    ggles
    1.01
     prove
    0.99
     satisfy
    0.91
     explore
    0.90
     spare
    0.90
     counteract
    0.90
    »Ĵ
    0.89
     conquer
    0.88
    Act Density 0.155%

    No Known Activations