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

    Neuronpedia

    INDEX
    Explanations

    situations involving moral dilemmas and the consequences of actions

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

    roles and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strconv
    -0.40
    aarrggbb
    -0.39
    MessageTagHelper
    -0.39
     pylori
    -0.38
    Cases
    -0.38
     incompetent
    -0.37
    ladiator
    -0.36
    ✥
    -0.36
     BorderSide
    -0.35
    Friend
    -0.35
    POSITIVE LOGITS
     ujednoznacz
    0.52
    曖昧さ回避
    0.47
    KommentareTeilen
    0.45
    èdia
    0.45
    AnchorStyles
    0.43
     helst
    0.41
    Diweddarwch
    0.40
    LookAnd
    0.39
    chets
    0.39
     utafitiHapana
    0.39
    Act Density 0.053%

    No Known Activations