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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulatory compliance and definitions

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

    words followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $_['
    -0.53
     skall
    -0.52
     Moslem
    -0.51
    wußt
    -0.50
     mußte
    -0.48
     quelquefois
    -0.47
     wußte
    -0.46
    ftagPool
    -0.46
     muß
    -0.46
     mempunyai
    -0.45
    POSITIVE LOGITS
     Notably
    0.71
    ponym
    0.71
     nuanced
    0.68
    …！
    0.66
    Alongside
    0.65
     underwhelming
    0.64
     famously
    0.62
    colades
    0.62
     Alongside
    0.61
     alongside
    0.61
    Act Density 0.428%

    No Known Activations