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

    Neuronpedia

    INDEX
    Explanations

    assertive statements regarding beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambi
    -0.20
     æ¥
    -0.16
    rist
    -0.16
    ê¸ī
    -0.15
    æ£
    -0.15
    arp
    -0.14
    à¹Ģ
    -0.14
    urrent
    -0.14
    uy
    -0.14
    946
    -0.14
    POSITIVE LOGITS
    oldt
    0.17
    PIO
    0.16
     Vine
    0.15
    iences
    0.15
     intr
    0.15
    ansen
    0.15
    rak
    0.15
     intra
    0.14
    endid
    0.14
    bjerg
    0.14
    Act Density 0.128%

    No Known Activations