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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols used in programming or markup languages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SizeMode
    -0.59
     Piso
    -0.57
    ionization
    -0.56
    arbeit
    -0.55
    IconModule
    -0.54
     Phrase
    -0.54
    disambiguation
    -0.52
    GHIJKLM
    -0.52
     Umbra
    -0.52
     parut
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    MockMvc
    0.64
     surla
    0.64
    ArgsConstructor
    0.63
     ddelweddau
    0.62
    RegressionTest
    0.57
    LookAnd
    0.56
    }');
    0.54
    aarrggbb
    0.53
    ">//
    0.53
    Act Density 0.004%

    No Known Activations