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

    Neuronpedia

    INDEX
    Explanations

    lists or compilations of information, such as tips or facts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate compilation or listing of items or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.72
     appar
    -0.61
    士
    -0.60
    morph
    -0.60
    izu
    -0.60
     [+
    -0.58
     Joined
    -0.58
    usional
    -0.57
    orage
    -0.57
    rador
    -0.56
    POSITIVE LOGITS
     infographic
    1.05
     rundown
    1.02
     POLITICO
    0.93
     HuffPost
    0.91
     roundup
    0.83
     countdown
    0.83
     recap
    0.81
     breakdown
    0.80
     highlights
    0.79
    Below
    0.77
    Act Density 0.401%

    No Known Activations