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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email communication and submission requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HING
    -0.14
    igh
    -0.13
    cid
    -0.13
     æł
    -0.13
    ishment
    -0.13
    aks
    -0.13
     derivatives
    -0.13
     Electric
    -0.13
     Canyon
    -0.13
    abet
    -0.13
    POSITIVE LOGITS
     Nack
    0.17
    latex
    0.17
    RLF
    0.15
    zcze
    0.15
    ottom
    0.15
    ghan
    0.15
     Tradable
    0.15
    æŁľ
    0.14
    lesi
    0.14
    вай
    0.14
    Act Density 0.037%

    No Known Activations