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

    Neuronpedia

    INDEX
    Explanations

    repeated or structural patterns in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    į¼
    -0.14
    оÑĪ
    -0.14
     spole
    -0.14
    nnen
    -0.14
    arte
    -0.13
    setChecked
    -0.13
    DIG
    -0.13
    vert
    -0.13
    λον
    -0.13
    $MESS
    -0.13
    POSITIVE LOGITS
    Transient
    0.15
    igaret
    0.15
     bell
    0.14
    tokens
    0.14
     Irene
    0.13
    óng
    0.13
    rup
    0.13
     Dual
    0.13
    iet
    0.13
    ch
    0.13
    Act Density 0.021%

    No Known Activations