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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voice-overs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.76
     Authority
    -0.75
     Journals
    -0.72
    Else
    -0.69
     brackets
    -0.69
     Triangle
    -0.69
    pillar
    -0.69
     drilling
    -0.69
     authority
    -0.68
    holders
    -0.67
    POSITIVE LOGITS
    ices
    1.25
    ICE
    1.23
    iced
    1.20
    oice
    1.16
    orde
    1.13
    ile
    1.08
    ise
    1.07
    okers
    1.00
    oker
    0.98
    isted
    0.97
    Act Density 0.585%

    No Known Activations