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

    Neuronpedia

    INDEX
    Explanations

    assertive statements regarding the existence or presence of conditions and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     two
    -0.24
    éĤ£äºĽ
    -0.21
    两个
    -0.20
     few
    -0.19
     three
    -0.18
    two
    -0.17
    åĩłä¸ª
    -0.17
     several
    -0.17
     chances
    -0.16
     многие
    -0.16
    POSITIVE LOGITS
     stuff
    0.25
     evidence
    0.23
     footage
    0.22
    stuff
    0.20
     Machinery
    0.20
     advice
    0.19
     machinery
    0.19
     weaponry
    0.18
     legislation
    0.18
     talk
    0.17
    Act Density 0.317%

    No Known Activations