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

    Neuronpedia

    INDEX
    Explanations

    references to creative writing techniques and their effectiveness

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

    methods and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onAttach
    -0.55
     فريبيس
    -0.54
    jsxFileName
    -0.49
     newOwner
    -0.48
     RIPRODUZIONE
    -0.48
    liflower
    -0.47
    rca
    -0.46
    бот
    -0.45
    strophy
    -0.45
    remia
    -0.44
    POSITIVE LOGITS
    fjspx
    0.57
     tactic
    0.50
     manipulation
    0.50
     tricks
    0.50
     manipulated
    0.50
     Manip
    0.50
     Manipulation
    0.50
     techniques
    0.48
    Manip
    0.48
     tactics
    0.47
    Act Density 0.269%

    No Known Activations