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

    Neuronpedia

    INDEX
    Explanations

    references to specific objects or entities within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
     ìĿ´ëĬĶ
    -0.15
     пÑĢавило
    -0.14
    INGLE
    -0.14
     creampie
    -0.12
    mour
    -0.12
     Bbw
    -0.12
    .hw
    -0.12
    andel
    -0.12
    ":[{↵
    -0.12
    POSITIVE LOGITS
    âĤ¬“
    0.17
    verts
    0.16
    /of
    0.15
    wards
    0.15
    sembl
    0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.14
    czy
    0.14
    aped
    0.13
    ients
    0.13
    /or
    0.13
    Act Density 0.504%

    No Known Activations