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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Mad" followed by various words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or entities associated with the term "Mad."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -1.11
    LECT
    -0.80
    IDER
    -0.75
    oldown
    -0.75
    ×Ļ×
    -0.74
    ORED
    -0.74
    chnology
    -0.73
    kefeller
    -0.71
    ORTS
    -0.71
    YE
    -0.69
    POSITIVE LOGITS
     Mad
    0.91
    agascar
    0.90
    mad
    0.81
    hya
    0.81
    eline
    0.80
    der
    0.78
    amaz
    0.78
    Mad
    0.77
    arus
    0.76
    bold
    0.76
    Act Density 0.004%

    No Known Activations