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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time duration or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uling
    -0.16
    geois
    -0.16
    deaux
    -0.16
    viso
    -0.15
    inya
    -0.15
    hiba
    -0.14
    лÑĥÑĪ
    -0.14
    resse
    -0.14
    achine
    -0.14
    sein
    -0.14
    POSITIVE LOGITS
     before
    0.28
    before
    0.21
     Before
    0.20
     shortly
    0.20
     first
    0.19
     they
    0.19
     forever
    0.19
     antes
    0.19
    Before
    0.18
     BEFORE
    0.18
    Act Density 0.039%

    No Known Activations