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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases indicating politeness or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discourse markers and hesitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.66
    IntoConstraints
    -0.61
     Administrativna
    -0.59
    хьтан
    -0.57
    GIVEREF
    -0.57
    webElementXpaths
    -0.57
     мәкал
    -0.57
    ⓧ
    -0.56
    libft
    -0.56
    Vidite
    -0.56
    POSITIVE LOGITS
    ということで
    0.70
     basically
    0.66
     básicamente
    0.65
    ちなみに
    0.65
    に関しては
    0.63
    というわけで
    0.63
    それにしても
    0.61
     tampaknya
    0.60
     dürfte
    0.60
    さすがに
    0.60
    Act Density 0.018%

    No Known Activations