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

    Neuronpedia

    INDEX
    Explanations

    past-tense verb phrases related to specific technical actions or changes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.90
     Rodham
    -0.83
     Pulitzer
    -0.82
     Teresa
    -0.79
     Dorothy
    -0.79
     Hers
    -0.75
     Wichita
    -0.74
     Faul
    -0.74
     Bethlehem
    -0.74
    CTV
    -0.73
    POSITIVE LOGITS
     devs
    1.44
     workaround
    1.40
     optimizations
    1.29
     implementations
    1.22
     implemented
    1.22
     optimization
    1.20
    fixes
    1.19
     tweaks
    1.18
     deprecated
    1.16
     tweak
    1.15
    Act Density 0.653%

    No Known Activations