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

    Neuronpedia

    INDEX
    Explanations

    verb forms related to actions and expectations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ss
    -0.18
    ennon
    -0.17
    496
    -0.15
    igans
    -0.15
     ourselves
    -0.15
    _NAMESPACE
    -0.15
    hart
    -0.14
    ahr
    -0.14
    sworth
    -0.14
    tn
    -0.14
    POSITIVE LOGITS
    -Mart
    0.16
    bic
    0.15
    heets
    0.15
    dol
    0.15
    akh
    0.14
    ì¶ĺ
    0.14
    edn
    0.14
    ansa
    0.14
     begr
    0.14
    med
    0.14
    Act Density 0.114%

    No Known Activations