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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating professional experience or tenure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ages
    -0.18
     ages
    -0.17
    194
    -0.15
    796
    -0.15
     WWII
    -0.14
    orough
    -0.14
    æ¬ł
    -0.14
    оÑĢоÑĤ
    -0.14
     zn
    -0.14
     ActionTypes
    -0.14
    POSITIVE LOGITS
    34
    0.21
    30
    0.20
    25
    0.19
    33
    0.19
    35
    0.19
    38
    0.18
    32
    0.18
    27
    0.18
     thirty
    0.17
    28
    0.16
    Act Density 0.060%

    No Known Activations