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

    Neuronpedia

    INDEX
    Explanations

    the word "as" followed by a description or explanatory clause

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as" followed by various contexts, indicating a focus on conditional or comparative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pez
    -0.72
    OUR
    -0.65
    âĹ¼
    -0.65
    Sharp
    -0.63
    åħ
    -0.61
    Ire
    -0.60
    GES
    -0.59
    IVE
    -0.59
    å½
    -0.59
    apons
    -0.58
    POSITIVE LOGITS
    piring
    1.21
    bestos
    1.21
    pires
    1.18
    piration
    1.17
    semb
    1.13
    phalt
    1.13
    pired
    1.09
    pects
    1.04
    semble
    1.04
    criptions
    0.99
    Act Density 0.128%

    No Known Activations