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

    Neuronpedia

    INDEX
    Explanations

    names or words related to political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities characterized by the term "erg."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.85
     Mub
    -0.74
    going
    -0.68
     Fram
    -0.67
    ©¶æ¥µ
    -0.63
    ften
    -0.62
    ĺħ
    -0.62
    fty
    -0.62
    LOAD
    -0.62
    creen
    -0.61
    POSITIVE LOGITS
    roup
    0.96
    ensen
    0.92
    raham
    0.90
    ling
    0.89
    reen
    0.89
    onomic
    0.87
    raphic
    0.87
    ues
    0.85
    roups
    0.84
    lings
    0.83
    Act Density 0.016%

    No Known Activations