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

    Neuronpedia

    INDEX
    Explanations

    references to secrets and secrecy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PyExc
    -0.91
     становника
    -0.84
    MigrationBuilder
    -0.81
     GetEnumerator
    -0.80
    帖最后由
    -0.80
     surla
    -0.80
    paravant
    -0.77
     defaultstate
    -0.74
    harusnya
    -0.71
    -0.71
    POSITIVE LOGITS
     secret
    3.66
     Secret
    3.39
    secret
    3.33
    Secret
    3.31
     SECRET
    3.06
     secrets
    2.87
     Secrets
    2.59
    SECRET
    2.57
    secrets
    2.42
    Secrets
    2.35
    Act Density 0.060%

    No Known Activations