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

    Neuronpedia

    INDEX
    Explanations

    references to bans and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بيها
    -0.81
    mtext
    -0.73
    s
    -0.71
    p
    -0.67
    tu
    -0.62
    mes
    -0.59
    e
    -0.58
    付
    -0.58
     Everett
    -0.56
     numberWith
    -0.56
    POSITIVE LOGITS
     bans
    1.43
     Bans
    1.34
     Bann
    1.28
     banning
    1.28
    Bans
    1.26
     banish
    1.15
     Banerjee
    1.13
    RemoveField
    1.11
    bans
    1.11
     banned
    1.10
    Act Density 0.141%

    No Known Activations