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

    Neuronpedia

    INDEX
    Explanations

    terms associated with product development and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -0.67
     
    -0.67
     the
    -0.60
     a
    -0.59
     N
    -0.57
     The
    -0.56
     an
    -0.56
     (
    -0.56
     to
    -0.55
     [
    -0.55
    POSITIVE LOGITS
    expandindo
    1.20
     propOrder
    1.09
    Vidite
    1.00
     itſelf
    0.96
     ་་
    0.94
     myſelf
    0.94
     doubtnut
    0.92
    featureID
    0.91
     raiſ
    0.89
     chofe
    0.87
    Act Density 0.601%

    No Known Activations