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

    Neuronpedia

    INDEX
    Explanations

    phrases related to daily news updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.82
    ©¶æ¥µ
    -0.77
    Card
    -0.71
    Constructed
    -0.69
     Incarn
    -0.65
    ãĥı
    -0.64
    Initialized
    -0.64
    abase
    -0.63
    ãĤ±
    -0.63
     Attempt
    -0.61
    POSITIVE LOGITS
     gossip
    0.94
     promotions
    0.91
     entertainment
    0.89
     rumours
    0.88
     analyses
    0.87
     analysis
    0.87
     commentary
    0.87
     rumors
    0.84
     trends
    0.83
     insights
    0.83
    Act Density 0.065%

    No Known Activations