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

    Neuronpedia

    INDEX
    Explanations

    references to key features or significant points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    алеж
    -0.16
    zzle
    -0.16
    件
    -0.16
    ikh
    -0.15
    handle
    -0.15
    zw
    -0.15
    load
    -0.14
    ãģ¹ãģį
    -0.14
    scape
    -0.14
    rf
    -0.14
    POSITIVE LOGITS
     reel
    0.20
    uated
    0.18
    ingly
    0.18
    ened
    0.18
     reels
    0.17
    eted
    0.17
    ighted
    0.16
    eting
    0.15
    uates
    0.15
    ting
    0.15
    Act Density 0.021%

    No Known Activations