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

    Neuronpedia

    INDEX
    Explanations

    phrases related to secrets or confidential information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confide" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.81
    Tur
    -0.60
     Roof
    -0.59
     practicable
    -0.58
     hardest
    -0.57
     Towards
    -0.57
    Ô
    -0.57
     Gamb
    -0.56
     Hope
    -0.55
     questioning
    -0.55
    POSITIVE LOGITS
    ederation
    1.42
    essional
    1.36
    luence
    1.35
    etti
    1.25
    eder
    1.24
    lag
    1.20
    ection
    1.18
    lated
    1.14
    idences
    1.12
    lation
    1.11
    Act Density 0.019%

    No Known Activations