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

    Neuronpedia

    INDEX
    Explanations

    words related to newness or recent events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eward
    -0.16
     destin
    -0.15
    venture
    -0.15
    lacak
    -0.15
    etin
    -0.15
    reach
    -0.15
    enef
    -0.14
    -notch
    -0.14
    ouz
    -0.14
     sooner
    -0.13
    POSITIVE LOGITS
     mint
    0.33
    mint
    0.24
    wed
    0.24
     Mint
    0.20
     formed
    0.20
     arrived
    0.19
     created
    0.19
     christ
    0.18
     newly
    0.18
    -formed
    0.18
    Act Density 0.014%

    No Known Activations