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

    Neuronpedia

    INDEX
    Explanations

    phrases related to catching someone's attention or interest

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various types of attention and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idia
    -0.85
     nomine
    -0.76
    enhagen
    -0.67
     fronts
    -0.67
     ensu
    -0.67
     unification
    -0.67
     fortun
    -0.66
    issance
    -0.64
     proxies
    -0.62
     horizont
    -0.62
    POSITIVE LOGITS
    tle
    0.83
    EMOTE
    0.73
     Lank
    0.72
    ById
    0.71
    OFF
    0.70
     whiff
    0.68
     trap
    0.68
    ancock
    0.68
    trap
    0.67
    ãĥīãĥ©
    0.67
    Act Density 0.118%

    No Known Activations