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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage taking a closer look or engaging deeply with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {}));
    -0.64
    verket
    -0.58
    +)/
    -0.57
    mení
    -0.57
     mekan
    -0.54
    )),
    -0.52
     stores
    -0.52
    fecture
    -0.50
    FieldOffset
    -0.50
    lewis
    -0.50
    POSITIVE LOGITS
     Anſ
    0.80
    сылкі
    0.79
     look
    0.77
     tslint
    0.76
     glancing
    0.76
    ValueStyle
    0.74
     Monfieur
    0.74
     kijk
    0.72
    kuuta
    0.70
    NOPQRST
    0.70
    Act Density 0.092%

    No Known Activations