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

    Neuronpedia

    INDEX
    Explanations

    programming-related language features and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rve
    -0.16
    phere
    -0.15
    >manual
    -0.14
    _Utils
    -0.14
     è¨Ģ
    -0.14
    >NN
    -0.14
    reu
    -0.14
     cigaret
    -0.14
    oined
    -0.14
    ostÃŃ
    -0.14
    POSITIVE LOGITS
    à¹Ĩ
    0.15
    /by
    0.15
     Esper
    0.15
    |
    0.14
     mission
    0.14
    çĪ½
    0.14
    usp
    0.14
    ä¸Ķ
    0.14
    =true
    0.14
     Affero
    0.13
    Act Density 0.119%

    No Known Activations