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

    Neuronpedia

    INDEX
    Explanations

    references to quantities, especially in the context of comparisons or accumulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iller
    -0.16
    ennen
    -0.14
    ModelProperty
    -0.14
    abin
    -0.14
    |int
    -0.13
    аÑİ
    -0.13
    .Param
    -0.13
    baar
    -0.13
    ail
    -0.13
    ior
    -0.13
    POSITIVE LOGITS
    -than
    0.16
     Mell
    0.16
    cente
    0.16
    ForEach
    0.16
    onta
    0.14
    ساÙĨ
    0.14
    ê»ĺ
    0.14
    llen
    0.14
     Richt
    0.14
    ThanOr
    0.14
    Act Density 0.050%

    No Known Activations