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

    Neuronpedia

    INDEX
    Explanations

    references to trolling behaviors and associated terms within online contexts

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

    troll, trolls, trolling, trolley, trolley museum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fut
    -0.36
    pely
    -0.35
    queous
    -0.35
     Infórmanos
    -0.34
    kespeare
    -0.34
     Require
    -0.33
     Equinox
    -0.33
    巳
    -0.33
     Uni
    -0.33
     =
    -0.32
    POSITIVE LOGITS
     troll
    2.14
     Troll
    1.91
     trolls
    1.89
    Troll
    1.88
    troll
    1.81
     trolling
    1.75
     trol
    1.23
     trolley
    0.91
    rolls
    0.88
     Trolley
    0.87
    Act Density 0.003%

    No Known Activations