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

    Neuronpedia

    INDEX
    Explanations

    terms related to time, such as hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categories or classifications, particularly those with recurring suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.81
    perty
    -0.80
     eas
    -0.62
    atche
    -0.61
    externalActionCode
    -0.61
     indifferent
    -0.60
     favour
    -0.58
    vous
    -0.58
    isance
    -0.58
    odka
    -0.56
    POSITIVE LOGITS
    ierre
    0.93
    arius
    0.86
    å°Ĩ
    0.82
    abase
    0.81
    ALLY
    0.76
    hyde
    0.75
    çĶŁ
    0.73
    lang
    0.72
    loe
    0.71
    akra
    0.70
    Act Density 0.152%

    No Known Activations