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

    Neuronpedia

    INDEX
    Explanations

    phrases that express trust or belief in someone's words or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repos
    -0.15
    ekil
    -0.15
    awah
    -0.14
    imary
    -0.14
    leton
    -0.14
    quets
    -0.14
    .sax
    -0.14
    apiro
    -0.14
    handled
    -0.14
     perhaps
    -0.14
    POSITIVE LOGITS
    imb
    0.16
    ÑĨеп
    0.15
    ingly
    0.14
    ãĥ¼ãĥĩ
    0.14
     vere
    0.14
    ably
    0.14
    ahn
    0.14
    548
    0.13
    Ùħج
    0.13
     Cove
    0.13
    Act Density 0.032%

    No Known Activations