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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures or appointed roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĩ£
    -0.18
    адж
    -0.15
    .notes
    -0.15
    nton
    -0.15
     PROCUREMENT
    -0.14
    orrent
    -0.14
    endale
    -0.14
    phoon
    -0.14
    iaÅĤa
    -0.13
    jte
    -0.13
    POSITIVE LOGITS
     веÑģ
    0.15
    ucci
    0.15
    éĽ
    0.14
    Та
    0.14
     President
    0.14
     Di
    0.14
    NONE
    0.13
     prime
    0.13
     Gratuit
    0.13
    inals
    0.13
    Act Density 0.113%

    No Known Activations