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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¥ŀ
    -0.78
     obser
    -0.76
     GENERAL
    -0.75
     confir
    -0.74
    660
    -0.74
     Saras
    -0.72
     circ
    -0.71
    ãģ®ç
    -0.71
    SOURCE
    -0.70
     1865
    -0.69
    POSITIVE LOGITS
    ett
    1.07
    etz
    1.06
    ick
    1.05
    ck
    1.02
    ack
    1.02
    et
    1.01
    icks
    0.98
    ik
    0.98
    cks
    0.97
    aq
    0.94
    Act Density 0.313%

    No Known Activations