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

    Neuronpedia

    INDEX
    Explanations

    places related to a city named "Mad" followed by numbers or other suffixes, such as "Madras" or "Madeline"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -1.05
    chnology
    -1.02
     Vaugh
    -0.83
    IDER
    -0.80
    oldown
    -0.79
    kefeller
    -0.77
    ×Ļ×
    -0.75
    çĦ
    -0.74
    LECT
    -0.72
    ylon
    -0.70
    POSITIVE LOGITS
    agascar
    1.04
    hya
    0.96
    rid
    0.96
    der
    0.92
    ras
    0.92
    eline
    0.91
    oka
    0.89
    cap
    0.85
    nit
    0.84
    hur
    0.82
    Act Density 0.015%

    No Known Activations