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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of warranties or conditions

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

    any kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.66
    \{\\
    -0.57
     surla
    -0.56
    __":
    -0.53
    ✨:
    -0.50
     Exactos
    -0.48
    __':
    -0.48
    Хьажоргаш
    -0.48
     GenerationType
    -0.48
     Polda
    -0.47
    POSITIVE LOGITS
     whatsoever
    0.60
     any
    0.57
     related
    0.50
     anything
    0.50
    任何
    0.49
     ANY
    0.48
    ftagPool
    0.46
     KIND
    0.46
     qualquer
    0.45
     absolut
    0.41
    Act Density 0.007%

    No Known Activations