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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Himo
    -0.53
     Гото
    -0.52
     vœ
    -0.51
    yaitu
    -0.50
    hicles
    -0.50
    $~
    -0.47
     manto
    -0.47
     Sebab
    -0.47
    Behold
    -0.47
     Phaser
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    1.06
     uintptr
    0.83
     Taktlose
    0.71
    RemoveField
    0.66
     للمعارف
    0.60
    ConstraintMaker
    0.60
    atguigu
    0.59
     Rued
    0.58
    fjspx
    0.56
    migrationBuilder
    0.56
    Act Density 0.060%

    No Known Activations