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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reviews
    -1.78
     cents
    -1.66
    ="$(
    -1.55
    »¿
    -1.49
    ftware
    -1.49
    journal
    -1.43
    aeda
    -1.41
     software
    -1.40
     publisher
    -1.37
     retailers
    -1.33
    POSITIVE LOGITS
     suspended
    1.70
     himself
    1.62
    grown
    1.62
     Guards
    1.60
     herself
    1.59
     screened
    1.59
    wash
    1.53
     divided
    1.50
     aligned
    1.50
     disturbed
    1.50
    Act Density 0.098%

    No Known Activations