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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political actions and sentiments, particularly in the context of societal issues

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

    Follows certain forms of "to be" verbs

    np_acts-logits-general · gemini-2.0-flash

    country conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themſelves
    -0.69
     myſelf
    -0.68
     himſelf
    -0.65
     Monfieur
    -0.57
     purpoſe
    -0.56
     Chriftian
    -0.56
     caufe
    -0.55
     pleaſure
    -0.54
     ſeveral
    -0.53
     poffe
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.83
    uxxxx
    0.68
    IUrlHelper
    0.66
    TagHelpers
    0.61
    EndTag
    0.60
     its
    0.60
     Its
    0.60
     ویکی‌پدیا
    0.58
    ectady
    0.57
    InitStruct
    0.56
    Act Density 0.579%

    No Known Activations