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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or tokens within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the start-of-sequence marker indicating the beginning of a text segment.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.53
     f
    -0.48
    BeginInit
    -0.48
     minOccurs
    -0.47
     getP
    -0.46
    XtraReports
    -0.45
    taler
    -0.45
    ServletConfig
    -0.44
     an
    -0.44
     pure
    -0.44
    POSITIVE LOGITS
     Italijanski
    0.70
    ismet
    0.68
    seamnă
    0.66
    UVWXYZ
    0.64
     feroit
    0.62
    ayaquil
    0.59
     houſe
    0.59
     tantum
    0.59
     hObject
    0.59
    ,:,
    0.58
    Act Density 0.372%

    No Known Activations