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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their relationships in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.15
    ("(%
    -0.14
    .serialization
    -0.14
    олом
    -0.14
    imity
    -0.14
    ENUM
    -0.13
    an
    -0.13
    -placeholder
    -0.13
     leakage
    -0.13
    holm
    -0.12
    POSITIVE LOGITS
    201
    0.19
    202
    0.15
    noinspection
    0.15
    ceptar
    0.15
    kos
    0.14
    acier
    0.14
    ingo
    0.14
    ypress
    0.13
     Spect
    0.13
    REW
    0.13
    Act Density 0.023%

    No Known Activations