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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "caught."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Applications
    -0.80
    Nob
    -0.70
    GROUP
    -0.65
    �
    -0.63
     premie
    -0.63
    神
    -0.62
     screenings
    -0.62
    iHUD
    -0.61
    Disk
    -0.60
    Studies
    -0.60
    POSITIVE LOGITS
    umber
    0.74
     cheating
    0.69
     asleep
    0.67
    rift
    0.67
     humming
    0.62
     red
    0.62
     between
    0.60
    chant
    0.60
     Archdemon
    0.60
    icut
    0.59
    Act Density 0.022%

    No Known Activations