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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discourse about professional actions and responsibilities

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

    reason for creation or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorizaciones
    -0.52
    気に入り
    -0.42
     Kurt
    -0.41
    莘
    -0.40
    ыре
    -0.40
    OOTDTY
    -0.40
     proven
    -0.40
     nonUne
    -0.40
    cray
    -0.40
     ep
    -0.39
    POSITIVE LOGITS
    的目的
    0.48
    objectif
    0.47
     primarily
    0.47
    SequentialGroup
    0.46
    ViewImports
    0.45
     głównie
    0.42
     هدف
    0.41
    verwijspagina
    0.41
     exclusiva
    0.41
     getIntent
    0.40
    Act Density 0.050%

    No Known Activations