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

    Neuronpedia

    INDEX
    Explanations

    references to flags

    oai_token-act-pair · gpt-3.5-turbo

    mentions of flags and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.81
    nesota
    -0.81
    axter
    -0.79
    soever
    -0.77
    lihood
    -0.76
    女
    -0.71
     subsequ
    -0.71
    arios
    -0.70
    nder
    -0.69
    è£ħ
    -0.69
    POSITIVE LOGITS
    pole
    1.30
    ging
    1.24
    rant
    1.15
    staff
    1.06
    inating
    0.88
     bearer
    0.87
    ged
    0.85
    Flag
    0.85
     flags
    0.80
     Flags
    0.80
    Act Density 0.025%

    No Known Activations