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

    Neuronpedia

    INDEX
    Explanations

    phrases related to publishing and document preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.13
    3:0.09
    4:0.04
    5:0.04
    6:0.10
    7:0.02
    8:0.05
    9:0.07
    10:0.30
    11:0.06
    Negative Logits
     Bans
    -1.65
     estates
    -1.62
    aceae
    -1.60
    issance
    -1.58
     Vand
    -1.55
    aterasu
    -1.55
    gling
    -1.55
     Faust
    -1.54
     Sod
    -1.54
    uctions
    -1.52
    POSITIVE LOGITS
     subtitles
    2.54
     transcript
    2.27
     transcription
    2.02
     transcripts
    1.84
     html
    1.80
     readable
    1.78
     embed
    1.77
    Subscribe
    1.76
     VIDE
    1.74
     rewritten
    1.70
    Act Density 0.001%

    No Known Activations