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

    Neuronpedia

    INDEX
    Explanations

    the combination of letters "En" followed by a single letter or a short word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "En" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.65
     Heights
    -0.64
     hitch
    -0.63
     independently
    -0.63
     distortion
    -0.62
    UGH
    -0.62
    OTH
    -0.61
    OHN
    -0.60
    DragonMagazine
    -0.60
    ooth
    -0.59
    POSITIVE LOGITS
    viron
    1.34
    chanted
    1.18
    closure
    1.17
    rollment
    1.16
    closed
    1.13
    riched
    1.10
    zyme
    1.09
    abling
    1.08
    forcer
    1.08
    cyclop
    1.08
    Act Density 0.023%

    No Known Activations