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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest significance or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombok
    -0.15
    ouden
    -0.15
    urb
    -0.14
    guard
    -0.14
     männ
    -0.13
    gil
    -0.13
    rende
    -0.13
    emer
    -0.13
    gii
    -0.13
    ntag
    -0.13
    POSITIVE LOGITS
    Ľi
    0.15
    038
    0.15
    ASON
    0.14
     Plaza
    0.14
    auc
    0.14
     rg
    0.14
    amura
    0.14
    anco
    0.13
    reason
    0.13
    _REASON
    0.13
    Act Density 0.034%

    No Known Activations