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

    Neuronpedia

    INDEX
    Explanations

    instances of sections and statuses in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clement
    -0.54
     виправивши
    -0.54
    Colin
    -0.54
     cruiser
    -0.54
    Clement
    -0.53
     candle
    -0.52
     capacitor
    -0.52
     credential
    -0.52
     commissioner
    -0.51
     carrot
    -0.51
    POSITIVE LOGITS
     Collins
    0.53
     Cs
    0.51
    Cs
    0.51
    SourceChecksum
    0.47
     cares
    0.46
     crores
    0.45
     carbons
    0.44
    KommentareTeilen
    0.42
    Collins
    0.42
    ECs
    0.42
    Act Density 0.981%

    No Known Activations