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

    Neuronpedia

    INDEX
    Explanations

    terms related to roles and structures in organizational or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onen
    -0.18
    ãĥ£
    -0.17
    ÏĢη
    -0.16
    fik
    -0.15
    anyahu
    -0.15
    åĵ¥
    -0.15
    .Accessible
    -0.14
     Harlem
    -0.14
    pire
    -0.14
    reator
    -0.14
    POSITIVE LOGITS
    415
    0.15
    .tm
    0.15
    rough
    0.15
    pras
    0.14
    Esc
    0.14
    esc
    0.14
     gangbang
    0.13
    ãĥ©ãĥ¼
    0.13
    -strokes
    0.13
    iles
    0.13
    Act Density 0.004%

    No Known Activations