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

    Neuronpedia

    INDEX
    Explanations

    textual references to rights and freedoms

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

    Follows a common verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    fiscal conservative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poffe
    -0.88
     pleaſure
    -0.87
     purpoſe
    -0.87
     abſ
    -0.84
     neceff
    -0.82
     tranſ
    -0.80
     ſever
    -0.78
     occaf
    -0.78
     eſſ
    -0.78
     deſt
    -0.77
    POSITIVE LOGITS
     whatnot
    0.81
     horrid
    0.71
     doings
    0.61
    ftagPool
    0.61
    wonderful
    0.60
     messed
    0.58
     monies
    0.58
     shoved
    0.57
     crap
    0.57
     wanting
    0.57
    Act Density 0.272%

    No Known Activations