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

    Neuronpedia

    INDEX
    Explanations

    references to tools and mechanisms related to assembly and disassembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.47
     Sauce
    -0.46
     مرجع
    -0.44
    zka
    -0.44
    поги
    -0.43
    anced
    -0.43
    ições
    -0.43
    足
    -0.43
    BeforeEach
    -0.42
    arbeitet
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.81
     levier
    0.80
     виправивши
    0.76
    #+#
    0.72
     puissiez
    0.70
     pulling
    0.69
    fjspx
    0.68
     pushing
    0.68
     suavemente
    0.67
     gently
    0.66
    Act Density 0.323%

    No Known Activations