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

    Neuronpedia

    INDEX
    Explanations

    words related to finality or decline

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dead" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.68
    omal
    -0.67
     CLSID
    -0.67
    %]
    -0.63
    zac
    -0.63
    ECA
    -0.62
    idate
    -0.61
     Cout
    -0.61
    ZX
    -0.60
     Libre
    -0.60
    POSITIVE LOGITS
    spin
    1.14
    locked
    1.12
    beat
    1.03
     reckoning
    0.99
    weight
    0.96
    liest
    0.96
    lier
    0.93
    heading
    0.91
    ening
    0.91
    locks
    0.88
    Act Density 0.030%

    No Known Activations