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

    Neuronpedia

    INDEX
    Explanations

    verbs in the infinitive form followed by another verb

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    selves
    -0.74
     unison
    -0.73
    processing
    -0.71
    growth
    -0.68
    results
    -0.63
     multiplying
    -0.63
     mutual
    -0.62
     discrep
    -0.61
    sembly
    -0.61
     occurring
    -0.60
    POSITIVE LOGITS
     himself
    1.31
     resign
    1.19
     veto
    1.16
     Himself
    1.08
     appoint
    0.97
     oversee
    0.95
     apologize
    0.91
     marry
    0.91
     personally
    0.89
     vetoed
    0.89
    Act Density 0.419%

    No Known Activations