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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wrapper
    -0.63
     antioxid
    -0.61
     Reborn
    -0.61
     Reloaded
    -0.60
    language
    -0.60
     Houses
    -0.59
     ancest
    -0.58
     Greenberg
    -0.58
     stabilized
    -0.58
     capacities
    -0.58
    POSITIVE LOGITS
     hesitate
    1.11
     bother
    1.07
     forget
    1.07
     underestimate
    0.94
     worry
    0.89
     expect
    0.88
     discriminate
    0.84
    erest
    0.84
    Í
    0.81
    intend
    0.80
    Act Density 0.046%

    No Known Activations