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

    Neuronpedia

    INDEX
    Explanations

    references to safeguarding or defending rights and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atan
    -0.15
    olley
    -0.15
    enstein
    -0.15
    egrator
    -0.15
    skb
    -0.14
    iggs
    -0.14
    erb
    -0.14
    ãĥ³ãĥģ
    -0.14
    aggi
    -0.14
    eter
    -0.14
    POSITIVE LOGITS
    ahl
    0.15
    èĦ
    0.14
     Spl
    0.13
    rost
    0.13
    ictionary
    0.13
    ably
    0.13
     horm
    0.13
     اÙĦÙħÙĪس
    0.13
    .fire
    0.13
    моÑĤ
    0.13
    Act Density 0.015%

    No Known Activations