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

    Neuronpedia

    INDEX
    Explanations

    instances of speech and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     according
    -0.19
     questions
    -0.15
     Questions
    -0.15
    ushima
    -0.15
    idas
    -0.15
     .
    -0.14
    ulta
    -0.14
     ._
    -0.14
    iej
    -0.14
     i
    -0.14
    POSITIVE LOGITS
     explan
    0.22
    HLT
    0.19
     erklä
    0.19
     explains
    0.16
    ylon
    0.16
    _ELEMENTS
    0.15
     conspir
    0.15
     explanation
    0.15
     explain
    0.15
     explaining
    0.15
    Act Density 0.064%

    No Known Activations