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

    Neuronpedia

    INDEX
    Explanations

    words associated with respect and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oma
    -0.16
    590
    -0.16
    inality
    -0.15
    ÌĢ
    -0.15
    elim
    -0.14
    ze
    -0.14
    iggs
    -0.14
     bullets
    -0.14
    LOC
    -0.14
     fix
    -0.14
    POSITIVE LOGITS
    ably
    0.21
    mund
    0.18
    habi
    0.17
    ãĥ¥
    0.15
    /stretch
    0.15
    .bootstrapcdn
    0.15
    .parameters
    0.14
    nyder
    0.14
    abil
    0.14
    .authenticate
    0.14
    Act Density 0.035%

    No Known Activations