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

    Neuronpedia

    INDEX
    Explanations

    Russian language characters, probably indicating some specific linguistic pattern

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'о' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.96
     Clover
    -0.81
    ometimes
    -0.80
    esville
    -0.79
    orsche
    -0.77
     Seym
    -0.76
    etsk
    -0.74
    mble
    -0.72
    raints
    -0.70
    ruciating
    -0.70
    POSITIVE LOGITS
    ÑĢ
    1.02
    Ñģ
    0.98
    н
    0.97
    Ñ
    0.95
    ÑĤ
    0.89
    е
    0.83
    cffffcc
    0.82
    Ì
    0.80
     Ð
    0.80
    ments
    0.79
    Act Density 0.019%

    No Known Activations