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

    Neuronpedia

    INDEX
    Explanations

    words related to strong emotions or sentiments, such as being saddened, disappointed, or appalled

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gravity
    -0.62
    zig
    -0.61
    Ranked
    -0.60
     nutshell
    -0.58
    illary
    -0.57
    aceutical
    -0.57
    essage
    -0.57
    ua
    -0.57
    entials
    -0.56
    zeb
    -0.55
    POSITIVE LOGITS
     by
    1.27
     aback
    1.05
    by
    1.01
    By
    0.93
     BY
    0.92
     By
    0.84
    dy
    0.80
     saddened
    0.73
     Dragonbound
    0.72
     anew
    0.71
    Act Density 0.109%

    No Known Activations