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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote conditions or statements regarding obligations and responsibilities

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

    of, about, concerning, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     linkovi
    -0.31
    astéro
    -0.27
     pungkasnya
    -0.26
     exporta
    -0.25
     treball
    -0.25
     Ekonomi
    -0.24
     historiador
    -0.24
    ecznie
    -0.23
     particularmente
    -0.23
     téléchargement
    -0.23
    POSITIVE LOGITS
    <unused8>
    0.71
    [@BOS@]
    0.71
    <unused28>
    0.71
    <unused41>
    0.71
    <unused52>
    0.71
    <unused47>
    0.71
    <unused68>
    0.71
    <unused74>
    0.71
    <unused3>
    0.71
    <unused43>
    0.71
    Act Density 0.157%

    No Known Activations