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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hierarchy and rank

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arat
    -0.17
    глÑı
    -0.16
    á»±c
    -0.16
    ento
    -0.16
    ì¶ľ
    -0.15
    éré
    -0.14
    chner
    -0.14
    à¥Įल
    -0.14
    217
    -0.14
    åij¨
    -0.14
    POSITIVE LOGITS
    hart
    0.21
    okoj
    0.14
    leet
    0.14
    ron
    0.14
    807
    0.14
     Princip
    0.13
     rab
    0.13
     principle
    0.13
    opup
    0.13
     grand
    0.13
    Act Density 0.017%

    No Known Activations