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

    Neuronpedia

    INDEX
    Explanations

    high-frequency function words and phrases that indicate relationships or conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISCO
    -0.18
    åĩĢ
    -0.16
    {text
    -0.16
    æŁı
    -0.15
    oria
    -0.15
     authDomain
    -0.14
    ÂĬ
    -0.14
    èħ¾
    -0.14
    RuleContext
    -0.14
     гÑĢо
    -0.14
    POSITIVE LOGITS
     individual
    0.26
     Individual
    0.25
    Individual
    0.21
    individual
    0.21
     individually
    0.18
     single
    0.17
     individuals
    0.17
     Ùģرد
    0.17
    个
    0.15
     individ
    0.15
    Act Density 0.007%

    No Known Activations