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

    Neuronpedia

    INDEX
    Explanations

    words related to expectations or anticipations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sawyer
    -0.71
    OOD
    -0.67
    enegger
    -0.65
     GOODMAN
    -0.65
    NING
    -0.64
    LIN
    -0.61
    WARE
    -0.61
     roofs
    -0.61
    die
    -0.60
     Rough
    -0.60
    POSITIVE LOGITS
    haust
    1.40
    terior
    1.30
    cerpt
    1.30
    ceptions
    1.26
    cessive
    1.25
    ternally
    1.23
    clamation
    1.21
    pert
    1.21
    pect
    1.17
    cludes
    1.16
    Act Density 0.021%

    No Known Activations