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

    Neuronpedia

    INDEX
    Explanations

    the word "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hör
    -0.68
     tagName
    -0.68
     Aner
    -0.67
     endfor
    -0.66
     Exc
    -0.65
    posedge
    -0.65
     '+':
    -0.65
     brightened
    -0.65
    setVerticalGroup
    -0.64
    greenrobot
    -0.64
    POSITIVE LOGITS
     итоге
    0.75
     eventually
    0.67
     become
    0.67
    interopRequire
    0.63
     actually
    0.61
     getting
    0.60
     Wirklichkeit
    0.59
    ویت
    0.58
     becoming
    0.58
     ultimately
    0.57
    Act Density 0.131%

    No Known Activations