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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal rules and the impact of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vae
    -0.17
    vore
    -0.16
    JD
    -0.14
    ASM
    -0.14
    lius
    -0.14
    kit
    -0.14
    nze
    -0.14
    etically
    -0.13
    uat
    -0.13
     {?>↵
    -0.13
    POSITIVE LOGITS
    ên
    0.14
    湯
    0.14
    人人
    0.14
    getc
    0.14
    ứ
    0.14
    ủ
    0.14
    .Guna
    0.14
    .fromFunction
    0.13
    ifestyles
    0.13
    criptor
    0.13
    Act Density 0.237%

    No Known Activations