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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "other" within textual contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    isters
    -0.75
     Bulg
    -0.74
    oir
    -0.71
    onics
    -0.69
    lectic
    -0.68
    ensibly
    -0.68
    wei
    -0.66
    ethe
    -0.65
    ister
    -0.64
    bda
    -0.64
    POSITIVE LOGITS
    worldly
    1.86
     aspect
    0.99
     entity
    0.91
    where
    0.89
     outlet
    0.89
     circumstance
    0.88
     major
    0.88
     mammal
    0.86
     thing
    0.86
     conceivable
    0.83
    Act Density 8.655%

    No Known Activations