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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by the word 'to'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pite
    -0.34
    Wan
    -0.34
    soever
    -0.33
    grounds
    -0.32
    afia
    -0.31
     Alleg
    -0.30
    ials
    -0.30
    iously
    -0.29
     Dawn
    -0.29
     Huma
    -0.29
    POSITIVE LOGITS
     reap
    0.44
    eat
    0.43
     hear
    0.42
     accomplish
    0.41
     achieve
    0.40
     earn
    0.40
     offend
    0.39
     get
    0.39
     lose
    0.39
     be
    0.39
    Act Density 9.189%

    No Known Activations