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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Thank" followed by a person or group

    np_acts-logits-general · gemini-2.0-flash

    thanks to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicidata
    -0.53
     cdti
    -0.51
     архивлан
    -0.51
    ByVersion
    -0.51
    뀜
    -0.50
    RuleContext
    -0.49
     whereas
    -0.49
    oise
    -0.49
    Carriera
    -0.48
     Ấ
    -0.48
    POSITIVE LOGITS
     whoever
    0.73
     ویکی‌پدیا
    0.66
    Whoever
    0.63
     whome
    0.59
     aDecoder
    0.57
    ArgsConstructor
    0.57
     coloro
    0.55
     Whoever
    0.55
    XDECREF
    0.55
     departments
    0.54
    Act Density 0.103%

    No Known Activations