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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to disclosure or uncovering hidden truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     U
    -0.68
     
    -0.68
     colspan
    -0.67
    läufe
    -0.66
    ymce
    -0.64
     or
    -0.62
    ecin
    -0.60
    ühungen
    -0.60
    aroni
    -0.59
    antMatchers
    -0.59
    POSITIVE LOGITS
     Reveal
    2.30
     reveal
    2.18
     revealed
    2.10
     reveals
    2.07
    reveal
    2.02
     Reveals
    1.98
    Reveal
    1.97
     Revealed
    1.95
     revealing
    1.95
    revealed
    1.89
    Act Density 0.068%

    No Known Activations