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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athan
    -0.16
    Sortable
    -0.15
    ProgressHUD
    -0.14
    avo
    -0.14
    xcb
    -0.14
    upd
    -0.14
     Latter
    -0.13
    throp
    -0.13
    ware
    -0.13
    rog
    -0.13
    POSITIVE LOGITS
    izza
    0.17
    luet
    0.17
    arp
    0.16
    foy
    0.14
     Together
    0.14
    TI
    0.14
     addCriterion
    0.14
    .argument
    0.14
    null
    0.14
    OLON
    0.14
    Act Density 0.001%

    No Known Activations