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

    Neuronpedia

    INDEX
    Explanations

    terms related to byproducts and their undesirable effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    byproduct and side effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    canestro
    -0.64
    fjspx
    -0.57
    :✨
    -0.57
    󠁧
    -0.54
    RTGC
    -0.52
    velas
    -0.51
     nawr
    -0.50
     Conform
    -0.48
    archical
    -0.48
     vectorielles
    -0.48
    POSITIVE LOGITS
     byproduct
    0.64
     Nebenwirkungen
    0.60
     побо
    0.59
     effects
    0.49
     consecuencias
    0.48
    副作用
    0.47
     effets
    0.46
     side
    0.46
     effect
    0.45
     conséquences
    0.45
    Act Density 0.059%

    No Known Activations