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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks such as commas

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulkan
    -0.79
    enaries
    -0.75
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.74
    ipment
    -0.74
     Vaugh
    -0.74
    anship
    -0.70
    ANS
    -0.69
    ures
    -0.67
    essor
    -0.67
     Kurds
    -0.66
    POSITIVE LOGITS
     lengthy
    0.75
    venge
    0.74
     sustained
    0.74
     quarter
    0.72
     convenient
    0.71
     straightforward
    0.71
     maiden
    0.70
     quick
    0.69
    stra
    0.69
     stagger
    0.69
    Act Density 0.000%

    No Known Activations