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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes or apostrophe-related contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scal
    -0.14
    aN
    -0.14
    bos
    -0.13
    ắn
    -0.13
     LAB
    -0.13
     Laboratories
    -0.13
    avs
    -0.13
    ocode
    -0.13
    .Chain
    -0.13
    311
    -0.13
    POSITIVE LOGITS
    undler
    0.15
    rophy
    0.15
     other
    0.15
    лом
    0.15
     Sokol
    0.14
    erb
    0.14
    PCM
    0.14
    ondon
    0.14
    imuth
    0.14
     Tep
    0.14
    Act Density 0.012%

    No Known Activations