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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation involving functions and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.52
     itſelf
    -1.52
     myſelf
    -1.47
     Efq
    -1.45
     houſe
    -1.43
    ſelves
    -1.42
     Houſe
    -1.41
     purpoſe
    -1.40
     Reſ
    -1.40
     ſtate
    -1.38
    POSITIVE LOGITS
     O
    0.65
     L
    0.65
    .
    0.60
     
    0.60
    ↵
    0.58
     o
    0.58
     v
    0.57
     ver
    0.57
     F
    0.56
     M
    0.55
    Act Density 0.100%

    No Known Activations