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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time duration

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    venants
    -0.68
    zona
    -0.68
    along
    -0.67
    yssey
    -0.64
    exclusive
    -0.64
    olan
    -0.64
    ogy
    -0.63
    sonian
    -0.63
     Converted
    -0.63
    buster
    -0.63
    POSITIVE LOGITS
     awhile
    1.17
     reasons
    1.10
     anymore
    1.05
     starters
    1.02
     anybody
    0.94
     purposes
    0.94
     anything
    0.93
     beginners
    0.91
     fear
    0.90
     foreseeable
    0.89
    Act Density 0.131%

    No Known Activations