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

    Neuronpedia

    INDEX
    Explanations

    mentions of rivers and waterfront properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .googleapis
    -0.16
    yd
    -0.15
    vider
    -0.15
    jom
    -0.15
    nost
    -0.15
    waters
    -0.15
    nob
    -0.14
    Ø·
    -0.14
    ục
    -0.14
    иÑĪ
    -0.14
    POSITIVE LOGITS
    dale
    0.19
     Plate
    0.17
    hack
    0.17
    boat
    0.17
     Kw
    0.16
    da
    0.16
    _rat
    0.15
    chia
    0.15
    ia
    0.15
    keeper
    0.15
    Act Density 0.018%

    No Known Activations