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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and positive emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ
    -0.15
    .space
    -0.15
    ameda
    -0.14
    azu
    -0.14
    ublic
    -0.14
     Sup
    -0.13
     replaces
    -0.13
    onda
    -0.13
    adamente
    -0.13
    argent
    -0.13
    POSITIVE LOGITS
    ph
    0.16
    .Generated
    0.15
    aker
    0.14
    .struts
    0.14
    pek
    0.14
    atr
    0.14
    /MIT
    0.14
    aria
    0.14
    &T
    0.14
    @section
    0.13
    Act Density 0.032%

    No Known Activations