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

    Neuronpedia

    INDEX
    Explanations

    words that convey positive attributes and achievements related to characters or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rams
    -0.15
     Pillow
    -0.14
    Intialized
    -0.14
    regs
    -0.14
    ÙĨØ©
    -0.14
    urum
    -0.14
     NSStringFromClass
    -0.14
     Schro
    -0.14
    airo
    -0.13
    hiro
    -0.13
    POSITIVE LOGITS
    éĨ
    0.16
    çĦ
    0.15
    otel
    0.15
     Äijây
    0.15
     Odyssey
    0.15
    Russ
    0.14
     disag
    0.14
     Bing
    0.14
     Russell
    0.14
    BUM
    0.14
    Act Density 0.030%

    No Known Activations