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

    Neuronpedia

    INDEX
    Explanations

    references to "machine" and "machine-related" terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     De
    -0.49
     
    -0.48
     Bea
    -0.47
     taking
    -0.46
     Charge
    -0.45
     di
    -0.45
     travel
    -0.45
     visited
    -0.44
     flu
    -0.44
    lip
    -0.44
    POSITIVE LOGITS
     itſelf
    0.73
     MACH
    0.65
    ſelf
    0.64
     Efq
    0.64
     leſs
    0.64
     Majefty
    0.60
     leaſt
    0.60
     whoſe
    0.60
     ſtand
    0.60
    Mach
    0.60
    Act Density 0.205%

    No Known Activations