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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and expressions of affirmation or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iddy
    -0.15
     Boeh
    -0.14
    )((((
    -0.14
    pton
    -0.14
    ãģıãĤĮãģŁ
    -0.13
    ida
    -0.13
     Suit
    -0.13
    hill
    -0.13
    662
    -0.13
    ndx
    -0.13
    POSITIVE LOGITS
    NECT
    0.15
     پاس
    0.15
    íħ
    0.15
    RESS
    0.14
    erokee
    0.14
    odiac
    0.14
    aycast
    0.14
    tring
    0.14
    inality
    0.13
    ossa
    0.13
    Act Density 0.008%

    No Known Activations