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

    Neuronpedia

    INDEX
    Explanations

    references to prohibitions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essentiel
    -0.64
    ertale
    -0.63
     equipe
    -0.62
     ryb
    -0.60
     Arteta
    -0.60
    ":[{
    -0.60
     core
    -0.59
     الوس
    -0.59
    %)$
    -0.58
     Dyke
    -0.58
    POSITIVE LOGITS
     bans
    1.39
     ban
    1.38
     Ban
    1.34
    Ban
    1.30
     BAN
    1.26
     banning
    1.26
     Bann
    1.21
    BAN
    1.18
     banish
    1.12
     Bans
    1.11
    Act Density 0.105%

    No Known Activations