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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences or subjective sentiments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    údo
    -0.57
      (
    -0.51
     And
    -0.51
     parah
    -0.48
     autorytatywna
    -0.48
    mayr
    -0.47
    ReusableCell
    -0.47
     ویکی
    -0.46
    tagext
    -0.46
     срока
    -0.46
    POSITIVE LOGITS
    istoitu
    0.68
    SBATCH
    0.64
     Efq
    0.64
     ſche
    0.63
     chofe
    0.62
    ſelf
    0.61
     Partagez
    0.61
    GHIJKLM
    0.59
     doubtnut
    0.58
     Abonnez
    0.57
    Act Density 0.029%

    No Known Activations