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

    Neuronpedia

    INDEX
    Explanations

    lens-related programming constructs and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     né
    -0.47
     W
    -0.46
     serviceName
    -0.45
     versus
    -0.42
     tewas
    -0.41
     Bu
    -0.41
    ↵↵
    -0.41
     nor
    -0.40
     '\\;'
    -0.40
     plus
    -0.40
    POSITIVE LOGITS
    ſelf
    0.76
    ⓧ
    0.76
     myſelf
    0.73
     reaſon
    0.72
     ſy
    0.71
     ſtate
    0.70
    ſelves
    0.69
     houſe
    0.69
     itſelf
    0.68
     pleaſure
    0.68
    Act Density 0.342%

    No Known Activations