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

    Neuronpedia

    INDEX
    Explanations

    words starting with the letters "wh"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tlement
    -0.17
    urum
    -0.15
    .dds
    -0.15
    rophe
    -0.15
    uegos
    -0.15
    ustry
    -0.15
    enez
    -0.15
    theid
    -0.14
    ulous
    -0.14
     Westbrook
    -0.14
    POSITIVE LOGITS
    soever
    0.21
    achat
    0.15
    foods
    0.15
    endale
    0.15
    aker
    0.15
     Vance
    0.14
    ath
    0.14
    ouse
    0.14
    arden
    0.14
     else
    0.14
    Act Density 0.020%

    No Known Activations