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

    Neuronpedia

    INDEX
    Explanations

    mentions of flags

    oai_token-act-pair · gpt-3.5-turbo

    references to flags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axter
    -0.72
    soever
    -0.70
    okin
    -0.70
    theless
    -0.70
    lihood
    -0.70
     Flavoring
    -0.67
    STD
    -0.67
    ãģ¦
    -0.65
    nesota
    -0.65
    Solution
    -0.64
    POSITIVE LOGITS
    pole
    1.19
     flags
    1.08
    rant
    1.08
     flag
    1.06
    flag
    1.01
    Flag
    0.99
     Flag
    0.98
    ging
    0.95
    staff
    0.87
     bearer
    0.85
    Act Density 0.007%

    No Known Activations