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

    Neuronpedia

    INDEX
    Explanations

    references to feelings of loss and mourning

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

    Following first-person pronouns expressing emotion

    np_acts-logits-general · gemini-2.0-flash

    ashamed/scared/thought/police

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.55
    KommentareTeilen
    -0.54
    esModule
    -0.54
    Segue
    -0.46
     Yule
    -0.46
    Gemeinden
    -0.45
    Essentially
    -0.45
     "..\..\..\
    -0.44
     simak
    -0.44
     bandoulière
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    tagHelperRunner
    0.72
    bür
    0.64
     shameless
    0.63
    ArgumentParser
    0.61
    kloped
    0.59
    usercontent
    0.58
     enmity
    0.58
     illogical
    0.58
     دیکھیے
    0.58
    Act Density 0.182%

    No Known Activations