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

    Neuronpedia

    INDEX
    Explanations

    symbols or notations commonly used in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     étoit
    -0.71
    parsedMessage
    -0.68
    featureID
    -0.68
    windowFixed
    -0.65
     myſelf
    -0.65
     avoient
    -0.63
     uſed
    -0.63
     themſelves
    -0.61
     raiſ
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
    ↵
    0.64
     “
    0.59
     trend
    0.57
      
    0.57
     de
    0.55
     
    0.55
    1
    0.54
     d
    0.53
     re
    0.53
     dis
    0.53
    Act Density 0.029%

    No Known Activations