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

    Neuronpedia

    INDEX
    Explanations

    references to banks and hospitalizations

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

    banks and hospitals

    np_acts-logits-general · gemini-2.0-flash

    bank and hospital contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hiro
    -0.47
     Ade
    -0.43
    enden
    -0.41
     McGee
    -0.41
    thi
    -0.41
     delights
    -0.41
    thre
    -0.40
     atraer
    -0.40
     Schal
    -0.40
    oui
    -0.40
    POSITIVE LOGITS
     Bank
    0.85
     BANK
    0.78
     bank
    0.76
    
    0.76
    Bank
    0.75
     Hospital
    0.75
     Banking
    0.70
    Hospital
    0.68
    BANK
    0.68
     Banker
    0.67
    Act Density 0.113%

    No Known Activations