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

    Neuronpedia

    INDEX
    Explanations

    references to updates and improvements in systems or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    retched
    -0.15
    ubern
    -0.14
    held
    -0.14
    -held
    -0.14
    ¤ëĭ¤
    -0.14
    _given
    -0.14
    ouble
    -0.13
     ASSIGN
    -0.13
    -setup
    -0.13
    rose
    -0.13
    POSITIVE LOGITS
     made
    0.28
    /add
    0.26
    /mod
    0.25
    made
    0.23
    /extensions
    0.22
     Made
    0.21
    /im
    0.21
     wrought
    0.20
    Made
    0.20
    ffect
    0.20
    Act Density 0.113%

    No Known Activations