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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing excess or extremes

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

    too followed by modifiers of excess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.54
    Fordítás
    -0.53
    pecabe
    -0.52
     avoient
    -0.51
    ientras
    -0.50
     Reſ
    -0.50
    berdayakan
    -0.49
     pleaſure
    -0.49
    EndTag
    -0.47
     Comprometido
    -0.46
    POSITIVE LOGITS
    too
    0.66
    Too
    0.62
     Too
    0.61
     too
    0.60
     TOO
    0.55
    TOO
    0.55
    Toole
    0.52
    ۜ
    0.51
     (!)
    0.51
    (!)
    0.51
    Act Density 0.005%

    No Known Activations