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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and connective phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urger
    -0.17
     eldre
    -0.16
    unsch
    -0.15
    许
    -0.14
     I
    -0.14
    onec
    -0.14
     Fate
    -0.14
     (
    -0.14
    IRT
    -0.14
     Lance
    -0.14
    POSITIVE LOGITS
     wor
    0.31
     da
    0.25
     ob
    0.25
     wom
    0.24
     sod
    0.24
     denn
    0.23
     was
    0.21
     indem
    0.21
     wo
    0.20
    doch
    0.19
    Act Density 0.017%

    No Known Activations