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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating contrast or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.19
     пÑĢавило
    -0.14
     ìĿ´ëĬĶ
    -0.14
     Bbw
    -0.14
    INGLE
    -0.13
     creampie
    -0.13
    ujet
    -0.13
    mour
    -0.12
    ÐļÐĺ
    -0.12
    ":[{↵
    -0.12
    POSITIVE LOGITS
    âĤ¬“
    0.17
    /of
    0.15
    verts
    0.15
    /or
    0.14
    wards
    0.14
    ÂĢÂ
    0.14
    zo
    0.13
    sembl
    0.13
    ients
    0.13
    aped
    0.13
    Act Density 0.522%

    No Known Activations