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

    Neuronpedia

    INDEX
    Explanations

    references to login actions or buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tänka
    -0.45
    onedDateTime
    -0.44
     medel
    -0.44
     Desenvolvimento
    -0.42
    InstanceState
    -0.41
    forderungen
    -0.39
     pensamento
    -0.39
    DeleteBehavior
    -0.38
     Warren
    -0.37
     Smal
    -0.37
    POSITIVE LOGITS
     Login
    1.07
    Login
    1.06
     login
    0.95
     logged
    0.94
     LOGIN
    0.89
     Logged
    0.85
    logged
    0.81
    login
    0.81
    LOGIN
    0.79
    登录
    0.75
    Act Density 0.250%

    No Known Activations