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

    Neuronpedia

    INDEX
    Explanations

    inquisitive phrases or statements that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owi
    -0.16
    еÑĢÑĪ
    -0.15
    isable
    -0.15
    rone
    -0.15
    ERC
    -0.14
    arently
    -0.14
    turnstile
    -0.14
    robat
    -0.14
    sert
    -0.14
    isers
    -0.14
    POSITIVE LOGITS
     slightly
    0.19
     even
    0.18
    ãĥ³ãĥķ
    0.17
    åIJ§
    0.17
    665
    0.14
    ance
    0.14
    ek
    0.14
    ãĤĤãģ£ãģ¨
    0.14
    .shiro
    0.14
     تÙĥÙĪÙĨ
    0.14
    Act Density 0.020%

    No Known Activations