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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives that emphasize the degree or intensity of descriptors

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ertodd
    -0.73
    rongh
    -0.70
    76561
    -0.70
    pta
    -0.67
    ULE
    -0.65
    ership
    -0.64
    ictions
    -0.63
    abouts
    -0.62
    %%
    -0.62
    ukong
    -0.62
    POSITIVE LOGITS
     impossible
    1.25
     ironic
    1.22
     easier
    1.19
     obvious
    1.16
     easy
    1.15
     advisable
    1.15
     conceivable
    1.14
     difficult
    1.13
     possible
    1.12
     feasible
    1.12
    Act Density 0.235%

    No Known Activations