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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to elaboration and clarification of details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.52
    NamedQuery
    -0.52
    AnimationFrame
    -0.48
    зайн
    -0.47
    彿
    -0.46
    InitStruct
    -0.45
     seguro
    -0.45
     mõ
    -0.44
    ComponentScan
    -0.43
     astore
    -0.42
    POSITIVE LOGITS
     clarify
    1.28
     elaboration
    1.20
     clarification
    1.20
     elaborated
    1.16
     explain
    1.16
     explanation
    1.14
     explanations
    1.08
     clarifying
    1.07
     explaining
    1.06
     clarified
    1.05
    Act Density 0.497%

    No Known Activations