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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ordering or positioning of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     erupt
    -0.62
    yo
    -0.61
    average
    -0.61
    bro
    -0.61
    mons
    -0.60
    elta
    -0.59
    orting
    -0.59
     demol
    -0.57
    ibles
    -0.57
     Murder
    -0.57
    POSITIVE LOGITS
     fearing
    1.31
     precaution
    1.23
    because
    1.10
     lest
    1.09
     because
    1.09
    Because
    1.05
     bec
    1.05
     fear
    1.00
    ecause
    0.99
     fears
    0.97
    Act Density 7.935%

    No Known Activations