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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statements or reflections of personal opinion

    oai_token-act-pair · gpt-3.5-turbo

    specific phrases or expressions about personal and societal grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.87
    NetMessage
    -0.77
    ģ«
    -0.76
    inent
    -0.76
    ĻĤ
    -0.76
    Ń·
    -0.70
     tremend
    -0.70
    utterstock
    -0.69
     cloning
    -0.69
    £ı
    -0.68
    POSITIVE LOGITS
    said
    1.22
     Said
    0.81
     said
    0.78
     exclaimed
    0.77
    Said
    0.74
    sed
    0.74
    ï¸ı
    0.71
     Verse
    0.70
    sung
    0.70
     wrote
    0.69
    Act Density 0.405%

    No Known Activations