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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future plans and project expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amm
    -0.17
    (Me
    -0.14
    ór
    -0.13
    ULE
    -0.13
     Replay
    -0.13
    affen
    -0.13
     Lew
    -0.13
    ington
    -0.13
     MMM
    -0.12
    282
    -0.12
    POSITIVE LOGITS
     online
    0.53
     operational
    0.49
    online
    0.48
    _online
    0.45
     ONLINE
    0.43
    -online
    0.41
     Online
    0.40
    Online
    0.40
    .online
    0.36
     Operational
    0.35
    Act Density 0.151%

    No Known Activations