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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations, such as cities or countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.82
     Unleashed
    -0.60
     snipp
    -0.58
    }}}
    -0.57
     Archangel
    -0.56
     hull
    -0.55
     Ember
    -0.55
     hover
    -0.55
     Avatar
    -0.54
     Cobra
    -0.54
    POSITIVE LOGITS
    ocre
    1.00
    coni
    0.90
    uti
    0.78
    acus
    0.78
    anwhile
    0.77
    ADRA
    0.77
    azeera
    0.76
    illions
    0.75
    uries
    0.73
    ogi
    0.73
    Act Density 0.082%

    No Known Activations