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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uant
    -0.16
    igan
    -0.15
    abler
    -0.15
    커ìĬ¤
    -0.15
    ÑģÑĤÑĥп
    -0.14
    oks
    -0.14
     preorder
    -0.14
     OnTrigger
    -0.13
    iology
    -0.13
    atical
    -0.13
    POSITIVE LOGITS
    erras
    0.16
    éry
    0.15
    gren
    0.15
    oger
    0.15
    .Region
    0.15
     dime
    0.14
    spam
    0.14
    .workspace
    0.14
    GY
    0.14
     experiment
    0.13
    Act Density 0.079%

    No Known Activations