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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and relationships between accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivre
    -0.16
    صÙĦ
    -0.15
    _MR
    -0.15
    gende
    -0.14
    WEEN
    -0.14
    plate
    -0.14
    lacak
    -0.14
    ÙĨع
    -0.14
     ëĦ¤ìĿ´íĬ¸
    -0.13
    -ser
    -0.13
    POSITIVE LOGITS
     Canvas
    0.39
    Canvas
    0.33
     course
    0.32
    (Canvas
    0.30
     canvas
    0.30
     Course
    0.29
    canvas
    0.28
    _canvas
    0.27
    .canvas
    0.27
    .Canvas
    0.27
    Act Density 0.029%

    No Known Activations