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

    Neuronpedia

    INDEX
    Explanations

    references to other people or groups

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

    "others" followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    actions towards others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JSTOR
    -0.65
    первых
    -0.64
     Miy
    -0.62
    /=
    -0.59
    gesteld
    -0.58
    ysław
    -0.58
    StringTo
    -0.57
     microfibra
    -0.57
     {_
    -0.56
     Wittenberg
    -0.55
    POSITIVE LOGITS
    worldly
    1.07
    InitVars
    0.90
    ništ
    0.72
     дописавши
    0.70
     Ferner
    0.67
    Portail
    0.67
    Geplaatst
    0.67
    था
    0.66
     than
    0.65
    帖最后由
    0.64
    Act Density 0.058%

    No Known Activations