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

    Neuronpedia

    INDEX
    Explanations

    words related to entities or activities characterized as rogue

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "rogue" states, entities, or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atsu
    -0.84
    ori
    -0.83
    ieu
    -0.76
    urity
    -0.74
    oret
    -0.72
    emporary
    -0.72
    ilar
    -0.71
    rix
    -0.70
    odcast
    -0.70
    uring
    -0.69
    POSITIVE LOGITS
    Rogue
    0.75
     rogue
    0.73
     thumb
    0.65
    bay
    0.64
    lings
    0.64
     Trader
    0.64
    finder
    0.63
     Rogue
    0.63
    blade
    0.62
     queens
    0.61
    Act Density 0.028%

    No Known Activations