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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places, particularly those including the word "Samar"

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAFT
    -0.77
    netflix
    -0.75
    nut
    -0.74
    puff
    -0.74
    rar
    -0.72
    rams
    -0.70
    spring
    -0.68
    bending
    -0.68
    oola
    -0.67
    ORN
    -0.66
    POSITIVE LOGITS
    itans
    1.00
     Samar
    0.90
    itan
    0.88
    pling
    0.85
    eness
    0.72
     Kou
    0.71
     Strip
    0.70
    ãĥ£
    0.69
    ©
    0.67
    µ
    0.66
    Act Density 0.047%

    No Known Activations