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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and queries related to familial interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģłãģijãģ©
    -0.17
    azzi
    -0.15
    ãģªãĤĵãģ¦
    -0.15
    ãĤıãģļ
    -0.14
    ãģ¡ãģ¯
    -0.13
    ãģijãĤĮãģ©
    -0.13
    isay
    -0.13
     Dont
    -0.13
    Whats
    -0.13
     ToDo
    -0.13
    POSITIVE LOGITS
    ~,
    0.20
    ãĢľ
    0.17
    ~-
    0.15
    ï½ŀ
    0.15
    ~~
    0.15
     ~(
    0.15
     nya
    0.14
     isn
    0.14
    ~
    0.14
     san
    0.14
    Act Density 0.033%

    No Known Activations