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

    Neuronpedia

    INDEX
    Explanations

    references to emotional and psychological impacts

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

    preceding "have" or similar verbs

    np_acts-logits-general · gemini-2.0-flash

    potential positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    luke
    -0.58
    agi
    -0.58
    Odpo
    -0.56
     Jaffe
    -0.53
     outputStream
    -0.52
    agin
    -0.52
    copg
    -0.51
    oprot
    -0.50
    AccessorTable
    -0.49
     Proofs
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.70
    awtextra
    0.68
     ofrecerte
    0.57
     offers
    0.56
     affords
    0.55
     offer
    0.55
    0.54
    resizingMask
    0.54
    Espèce
    0.53
     oferecer
    0.53
    Act Density 0.294%

    No Known Activations