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

    Neuronpedia

    INDEX
    Explanations

    references to groundbreaking or innovative ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ford
    -0.18
    rades
    -0.18
    Howard
    -0.18
     Howard
    -0.17
    ächst
    -0.17
    apı
    -0.16
     cure
    -0.16
    lej
    -0.15
    eh
    -0.15
     Sp
    -0.15
    POSITIVE LOGITS
    sey
    0.17
    çĩ
    0.16
    iform
    0.15
    olik
    0.14
    _pb
    0.14
     bản
    0.14
    etti
    0.14
    latable
    0.14
     Bek
    0.14
     Civil
    0.14
    Act Density 0.025%

    No Known Activations