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

    Neuronpedia

    INDEX
    Explanations

    references to time periods such as months, weeks, and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    νÏĦ
    -0.15
    eras
    -0.15
    argent
    -0.15
    ëĭĪìĬ¤
    -0.14
    ostat
    -0.14
    arend
    -0.14
    /compiler
    -0.14
    heiro
    -0.13
    amedi
    -0.13
    quist
    -0.13
    POSITIVE LOGITS
     later
    0.36
     ago
    0.34
     Ago
    0.29
     Later
    0.28
     into
    0.27
     down
    0.25
    later
    0.25
     earlier
    0.24
    Later
    0.23
     latter
    0.23
    Act Density 0.070%

    No Known Activations