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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and other common function words that suggest actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipop
    -0.15
    _Save
    -0.15
    Ñ
    -0.14
    iosper
    -0.14
    itsu
    -0.14
    letion
    -0.14
    engeance
    -0.14
    593
    -0.14
    arge
    -0.14
    ighb
    -0.14
    POSITIVE LOGITS
    ALA
    0.15
    DIC
    0.14
     Bord
    0.14
    affiliate
    0.14
     cham
    0.14
    è£
    0.14
    uhn
    0.13
    ember
    0.13
    ifar
    0.13
    说è¯Ŀ
    0.13
    Act Density 0.002%

    No Known Activations