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

    Neuronpedia

    INDEX
    Explanations

    transactions and numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific films and their corresponding financial success or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trough
    -0.86
     notation
    -0.85
     denomin
    -0.81
     disadvantage
    -0.73
    vt
    -0.73
    fters
    -0.71
     certific
    -0.70
     administr
    -0.69
    rb
    -0.69
     markup
    -0.69
    POSITIVE LOGITS
     Terminator
    1.23
     Ghostbusters
    1.22
     Sleeping
    1.21
     Moonlight
    1.19
     Gravity
    1.19
     Firefly
    1.19
     Transformers
    1.17
     Hunger
    1.17
     Gladiator
    1.16
     Notting
    1.15
    Act Density 0.216%

    No Known Activations