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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and informal speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nicknames and informal addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hjemmes
    -0.42
    RegistryLite
    -0.41
     مشين
    -0.40
     âges
    -0.40
     extra
    -0.40
     Diener
    -0.38
     Crian
    -0.37
     âge
    -0.36
     noted
    -0.35
     nivelul
    -0.34
    POSITIVE LOGITS
     homie
    0.58
    +#+
    0.57
    #+#
    0.52
     فريبيس
    0.52
     buddy
    0.50
    EndGlobalSection
    0.49
     dudes
    0.49
     comrade
    0.48
     guys
    0.47
     footy
    0.47
    Act Density 0.143%

    No Known Activations