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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or considerations of entirety in discussions

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

    all of / both of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.50
     pinulongan
    -0.50
     felicitación
    -0.49
    ffilm
    -0.49
     vœ
    -0.48
     conmigo
    -0.48
     pysty
    -0.47
    tvguidetime
    -0.47
     uska
    -0.47
     zijne
    -0.46
    POSITIVE LOGITS
    part
    0.47
     part
    0.45
     GenerationType
    0.42
    Parts
    0.40
     Sumo
    0.40
    partie
    0.39
     All
    0.39
    All
    0.39
     parts
    0.39
    parts
    0.38
    Act Density 0.020%

    No Known Activations