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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate involvement or presence in historical or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    islav
    -0.19
    ios
    -0.16
    .instrument
    -0.16
    xit
    -0.15
     citt
    -0.14
    ellen
    -0.14
    orgh
    -0.14
    _IO
    -0.14
    JO
    -0.14
    rog
    -0.14
    POSITIVE LOGITS
     circulation
    0.31
     existence
    0.27
     service
    0.23
     operation
    0.22
     active
    0.22
     custody
    0.21
     production
    0.21
     rotation
    0.20
     contention
    0.19
    existence
    0.19
    Act Density 0.118%

    No Known Activations