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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.81
    heid
    -0.75
    RAW
    -0.74
    DragonMagazine
    -0.74
    isks
    -0.72
    IRE
    -0.68
    BILITIES
    -0.67
    erity
    -0.67
    few
    -0.66
    UTH
    -0.66
    POSITIVE LOGITS
     portraying
    1.15
     explaining
    1.09
     educating
    1.07
     integrating
    1.03
     keeping
    1.01
     balancing
    1.01
     justifying
    1.00
     illustrating
    1.00
     distinguishing
    0.96
     showcasing
    0.95
    Act Density 0.041%

    No Known Activations