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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "can" and its variations, indicating a focus on ability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tonel
    -0.59
     seç
    -0.49
     hiper
    -0.49
     stimm
    -0.49
     cristales
    -0.47
    PathVariable
    -0.47
    ores
    -0.47
    #!/
    -0.46
    EventBus
    -0.45
     {
    -0.44
    POSITIVE LOGITS
    Rüyada
    0.74
    __(/*!
    0.71
    phosa
    0.69
    ArrowToggle
    0.69
    migrationBuilder
    0.69
    sidemargin
    0.67
     esternos
    0.67
    الدراسه
    0.67
     препратки
    0.65
    höhung
    0.64
    Act Density 0.309%

    No Known Activations