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

    Neuronpedia

    INDEX
    Explanations

    the word "favor" or "favour" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating support or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ı
    -0.69
     Bam
    -0.64
    Wallet
    -0.61
    ridges
    -0.59
     laun
    -0.58
    borg
    -0.57
     Thumbnails
    -0.57
    DragonMagazine
    -0.57
    INFO
    -0.57
    ember
    -0.56
    POSITIVE LOGITS
    itism
    1.84
    ited
    1.06
    ably
    1.00
    ites
    0.96
    ability
    0.89
    itive
    0.84
     favoring
    0.83
    itely
    0.82
    ite
    0.77
    iting
    0.75
    Act Density 0.057%

    No Known Activations