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

    Neuronpedia

    INDEX
    Explanations

    the name "Hal" followed by various words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    the name "Hal" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.81
    URES
    -0.79
    URE
    -0.75
    âĶģ
    -0.71
    ãģį
    -0.71
    ãģķ
    -0.70
    æĸ¹
    -0.69
    ULTS
    -0.67
     nomine
    -0.64
    REDACTED
    -0.64
    POSITIVE LOGITS
    ifax
    1.26
    ftime
    1.13
    iday
    1.07
    ibur
    1.06
    ocaust
    1.04
    ogen
    1.04
    tering
    1.02
    ving
    0.98
    iber
    0.94
    tered
    0.91
    Act Density 0.026%

    No Known Activations