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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belief, opinion, or evaluation regarding complex matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quette
    -0.17
    noÅĽci
    -0.15
    ¬ģ
    -0.15
    claimer
    -0.15
    aggi
    -0.14
    planation
    -0.14
    assi
    -0.14
    icas
    -0.14
    tera
    -0.14
    Äĩi
    -0.13
    POSITIVE LOGITS
    shell
    0.15
     Cob
    0.14
     shell
    0.14
    IRD
    0.14
     core
    0.14
    sembled
    0.14
    _qs
    0.13
    ÑĢел
    0.13
     Base
    0.13
     Shell
    0.13
    Act Density 0.105%

    No Known Activations