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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific addresses and details in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carlin
    -1.03
     Sis
    -0.92
     latter
    -0.80
    kates
    -0.78
     Bader
    -0.78
    nsic
    -0.77
    enchymal
    -0.76
    Sis
    -0.76
     restTemplate
    -0.75
    🔥🔥
    -0.74
    POSITIVE LOGITS
    ing
    2.58
    ING
    1.77
    ة
    1.04
    ingh
    0.93
    ی
    0.91
    ingi
    0.88
    izing
    0.88
    ingan
    0.85
    ating
    0.83
    ging
    0.80
    Act Density 0.410%

    No Known Activations