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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve negation or disclaimers regarding beliefs or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.78
    awtextra
    -0.73
    Hentet
    -0.72
     ddelweddau
    -0.68
    enumi
    -0.64
     ExecuteAsync
    -0.64
    stuffs
    -0.63
    tvguidetime
    -0.63
    windowFixed
    -0.62
    IsContent
    -0.60
    POSITIVE LOGITS
    otek
    0.48
     do
    0.47
    ictwa
    0.44
    диви
    0.43
     individual
    0.43
     surla
    0.43
     or
    0.43
    UpInside
    0.42
    unmodifiable
    0.42
     But
    0.42
    Act Density 0.277%

    No Known Activations