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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating differing perspectives or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.65
    pecabe
    -0.65
    󠁴
    -0.61
     houſe
    -0.55
     saveiro
    -0.55
    ⤹
    -0.54
    contentLoaded
    -0.54
    findpost
    -0.53
    RenderAtEndOf
    -0.53
    titleMargin
    -0.52
    POSITIVE LOGITS
     probably
    0.47
     Probably
    0.40
    Probably
    0.40
     deserve
    0.38
     ought
    0.35
     prolly
    0.34
    probably
    0.33
    ListItemIcon
    0.33
     gd
    0.33
     really
    0.33
    Act Density 1.454%

    No Known Activations