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

    Neuronpedia

    INDEX
    Explanations

    sections of text that start with the token "<bos>", indicating the beginning of a new segment or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.75
    ioutil
    -0.73
    }}^{(
    -0.70
    complexType
    -0.66
    RegressionTest
    -0.65
     TextEditing
    -0.65
    Abp
    -0.65
    PageIndex
    -0.64
     AssemblyProduct
    -0.64
    UnknownFields
    -0.64
    POSITIVE LOGITS
     hanging
    1.23
     hung
    1.15
    hanging
    1.14
    Hanging
    1.08
     Hanging
    1.07
     hangs
    1.07
     hanged
    1.00
     suspendu
    0.99
     hang
    0.97
    Suspended
    0.94
    Act Density 0.036%

    No Known Activations