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

    Neuronpedia

    INDEX
    Explanations

    references to media outlets and news stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hlav
    -0.15
    iore
    -0.15
    ties
    -0.15
    _tC
    -0.14
    -toggler
    -0.14
     Bush
    -0.14
    blk
    -0.14
     prof
    -0.14
    []={
    -0.14
    liner
    -0.14
    POSITIVE LOGITS
    artin
    0.17
     dust
    0.16
    IEW
    0.15
     Weekly
    0.15
     Nichols
    0.15
    δη
    0.15
    OLA
    0.14
     altro
    0.14
    ARIO
    0.14
     belt
    0.14
    Act Density 0.032%

    No Known Activations