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

    Neuronpedia

    INDEX
    Explanations

    various types of numerical values or counts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ong
    -0.18
    ÑģÑĮ
    -0.16
    .codec
    -0.16
     Rossi
    -0.15
    ibase
    -0.15
    junction
    -0.14
    ute
    -0.14
    ëĮĢë¡ľ
    -0.14
     Survival
    -0.13
    ãģķãģĽ
    -0.13
    POSITIVE LOGITS
    529
    0.15
    aterno
    0.14
    orsk
    0.14
     bulls
    0.14
    entes
    0.14
    522
    0.14
    aÅŁ
    0.14
    Ïİν
    0.14
    illard
    0.13
    ailles
    0.13
    Act Density 0.001%

    No Known Activations