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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions related to validation and nullity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allet
    -0.17
    endar
    -0.15
    owl
    -0.15
    -shopping
    -0.14
     Moss
    -0.14
    indow
    -0.14
     giants
    -0.14
    åĿĤ
    -0.14
    FU
    -0.14
    lane
    -0.14
    POSITIVE LOGITS
    iani
    0.17
    Propagation
    0.15
    «
    0.14
     folds
    0.14
    iom
    0.14
    315
    0.14
    NX
    0.14
    imer
    0.14
     Cave
    0.14
     hidden
    0.13
    Act Density 0.125%

    No Known Activations