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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "more" indicating an increase or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.81
     tantôt
    -0.79
     auroit
    -0.71
    ſelves
    -0.70
     Efq
    -0.70
     ciasc
    -0.69
     religione
    -0.69
     ejus
    -0.68
     mariée
    -0.68
     pitié
    -0.68
    POSITIVE LOGITS
     incredible
    0.65
     comp
    0.63
     outstanding
    0.60
     Team
    0.58
    ThemeOverlay
    0.57
    SuppressLint
    0.57
     release
    0.55
    ↵
    0.55
     uns
    0.55
     enormous
    0.54
    Act Density 0.047%

    No Known Activations