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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb indicating some form of action or condition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.65
     Flavoring
    -0.63
    math
    -0.60
    vine
    -0.60
     Gerard
    -0.60
     Tet
    -0.60
     unspecified
    -0.59
    Diff
    -0.58
    Reviewer
    -0.57
     Fine
    -0.57
    POSITIVE LOGITS
    've
    1.04
     envisioned
    1.02
     chose
    0.98
     dreamed
    0.94
    're
    0.93
     grew
    0.91
     swore
    0.91
     inherited
    0.90
     adore
    0.86
     cherish
    0.86
    Act Density 0.106%

    No Known Activations