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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating organizational roles and titles

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

    director of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.41
    oa̍t
    -0.41
    éndolo
    -0.38
     décoration
    -0.37
    სქოლიო
    -0.35
     minimalista
    -0.34
     vôtre
    -0.33
    tiéndose
    -0.33
    ContentLoaded
    -0.33
     hipótesis
    -0.33
    POSITIVE LOGITS
    +#+
    0.65
    tagHelperRunner
    0.53
    BeginContext
    0.53
    новниш
    0.52
     argint
    0.52
    ########.
    0.51
    っそ
    0.47
     Roy
    0.47
    0.47
     the
    0.46
    Act Density 0.006%

    No Known Activations