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

    Neuronpedia

    INDEX
    Explanations

    references to letters and written communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    991
    -0.15
    alse
    -0.15
    iskey
    -0.14
    925
    -0.14
    etsk
    -0.14
    518
    -0.14
     pl
    -0.13
    porter
    -0.13
     sources
    -0.13
    769
    -0.13
    POSITIVE LOGITS
     addressed
    0.22
     letter
    0.19
    letter
    0.17
     LETTER
    0.17
    -letter
    0.16
     Letter
    0.15
     letters
    0.15
    èĤī
    0.15
     sender
    0.15
    .sender
    0.15
    Act Density 0.114%

    No Known Activations