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

    Neuronpedia

    INDEX
    Explanations

    phrases that express frequency or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.17
    ãng
    -0.16
    efon
    -0.15
    æµİ
    -0.14
    ovsky
    -0.14
    -feedback
    -0.14
    ono
    -0.14
     mastur
    -0.14
    ersive
    -0.14
    inas
    -0.14
    POSITIVE LOGITS
     Scri
    0.17
    ble
    0.16
    acket
    0.16
    SCI
    0.14
     indeed
    0.14
    .cn
    0.14
     cooper
    0.13
     Eisen
    0.13
     am
    0.13
     partic
    0.13
    Act Density 0.180%

    No Known Activations