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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing subjective opinions about experiences or conditions

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

    Comes before adjectives of degree

    np_acts-logits-general · gemini-2.0-flash

    a little bit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.94
     myſelf
    -0.92
     Monfieur
    -0.79
     himſelf
    -0.78
     ſtate
    -0.78
     itſelf
    -0.77
     themſelves
    -0.77
     fubject
    -0.73
    ſelf
    -0.72
     reaſon
    -0.72
    POSITIVE LOGITS
     i
    0.88
     crazy
    0.75
     funky
    0.72
     kinda
    0.66
     kind
    0.66
     weird
    0.65
     sorta
    0.63
     dice
    0.63
     nuts
    0.62
     sketchy
    0.61
    Act Density 0.221%

    No Known Activations