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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate risk or uncertainty

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

    with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.54
    msgTypes
    -0.52
     Houſe
    -0.52
     AppColors
    -0.52
     mergeFrom
    -0.52
     Chwiliwch
    -0.51
     leaſt
    -0.51
     désolés
    -0.50
    licability
    -0.49
     defaultstate
    -0.49
    POSITIVE LOGITS
     waarmee
    0.57
     womit
    0.55
     kanssa
    0.49
    with
    0.48
    Personendaten
    0.45
    With
    0.45
     With
    0.44
     Damit
    0.44
    Avec
    0.44
     conmigo
    0.44
    Act Density 0.118%

    No Known Activations