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

    Neuronpedia

    INDEX
    Explanations

    strong expressions of belief or conviction regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.17
    ewise
    -0.17
    ewe
    -0.15
    urgence
    -0.15
    antino
    -0.15
    à¹Ĥ
    -0.15
    brig
    -0.14
    buch
    -0.14
    endar
    -0.14
    èĪĪ
    -0.14
    POSITIVE LOGITS
     inc
    0.16
     strongly
    0.16
     om
    0.16
     emb
    0.14
    sku
    0.14
    si
    0.14
     equ
    0.14
    ìŀij
    0.14
     capabilities
    0.13
    -trans
    0.13
    Act Density 0.039%

    No Known Activations