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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or hedging language

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

    Comes before "I," "it," "they," or "you"

    np_acts-logits-general · gemini-2.0-flash

    consequence or reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.69
    ſelf
    -0.67
     Reſ
    -0.66
     Majefty
    -0.66
    ſelves
    -0.66
     Winfrey
    -0.65
     Anſ
    -0.65
     Efq
    -0.64
     Houſe
    -0.62
     Monfieur
    -0.62
    POSITIVE LOGITS
     it
    0.80
    StructEnd
    0.76
     yeah
    0.74
     defaultstate
    0.74
    UnknownFieldSet
    0.73
     maybe
    0.72
     therefor
    0.71
     let
    0.71
     I
    0.70
     hopefully
    0.69
    Act Density 0.141%

    No Known Activations