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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product launches and announcements

    oai_token-act-pair · gpt-3.5-turbo

    actions related to product launches and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.83
    hene
    -0.80
    taboola
    -0.80
    chan
    -0.79
    fax
    -0.77
    sein
    -0.74
    hoe
    -0.74
    Merit
    -0.73
    pac
    -0.73
    "]=>
    -0.73
    POSITIVE LOGITS
     prototypes
    0.87
     its
    0.81
     new
    0.78
     standalone
    0.78
     DRAGON
    0.78
     plans
    0.77
     another
    0.76
     a
    0.74
     their
    0.73
     redesigned
    0.71
    Act Density 0.213%

    No Known Activations