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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters such as apostrophes and dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Detail
    -0.76
     Flavoring
    -0.73
     Rouge
    -0.73
    ĺħ
    -0.68
     Container
    -0.65
    ĸļ
    -0.64
     Citation
    -0.63
     Heist
    -0.62
     Crusader
    -0.61
     Reloaded
    -0.61
    POSITIVE LOGITS
    present
    0.85
    clad
    0.79
    ifiable
    0.79
     awoken
    0.78
     contemplated
    0.73
    mint
    0.73
    married
    0.72
    arded
    0.71
    installed
    0.70
    iciary
    0.70
    Act Density 0.090%

    No Known Activations