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

    Neuronpedia

    INDEX
    Explanations

    instances of manipulation and control in societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posable
    -0.18
    ãħİ
    -0.14
    \admin
    -0.14
    itre
    -0.13
     compet
    -0.13
    yen
    -0.13
    ì§ķ
    -0.13
    uplic
    -0.13
    ocked
    -0.13
    nt
    -0.13
    POSITIVE LOGITS
    agrid
    0.16
    baum
    0.15
    achat
    0.15
    İ
    0.14
    .reloadData
    0.14
    shortcode
    0.14
    enta
    0.14
    Âİ
    0.14
    ëł
    0.13
    CF
    0.13
    Act Density 0.725%

    No Known Activations