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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating actions or states of being that follow the pattern "subject + verb."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     beforehand
    -0.78
     initially
    -0.77
    ascript
    -0.67
     prior
    -0.63
     Initially
    -0.62
     previous
    -0.59
    oused
    -0.58
    arine
    -0.58
    odor
    -0.58
     predecessor
    -0.57
    POSITIVE LOGITS
    here
    0.88
     reckoning
    0.70
     finally
    0.68
     officially
    0.68
    nir
    0.68
     reality
    0.66
     realize
    0.65
     realise
    0.65
    adays
    0.64
     gotta
    0.64
    Act Density 0.230%

    No Known Activations