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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude directed towards individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lassen
    -0.17
    leans
    -0.17
    rada
    -0.16
    apr
    -0.16
    ondo
    -0.15
    usto
    -0.15
    oro
    -0.15
    iston
    -0.15
    ampo
    -0.14
    ÂĢÂ
    -0.14
    POSITIVE LOGITS
    aliz
    0.20
    uu
    0.19
    istrovstvÃŃ
    0.18
    åĢij
    0.16
    yers
    0.16
    elson
    0.15
    /us
    0.15
    gere
    0.15
    ’re
    0.14
    ãģĶãģĸãģĦãģ¾ãģĻ
    0.14
    Act Density 0.010%

    No Known Activations