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

    Neuronpedia

    INDEX
    Explanations

    words related to covering or concealing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to concealment or covering in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recomm
    -0.78
     onwards
    -0.70
    friend
    -0.65
     AAA
    -0.63
     rever
    -0.63
     chau
    -0.60
     overpowered
    -0.60
     inertia
    -0.60
    esson
    -0.59
     recogn
    -0.59
    POSITIVE LOGITS
    topic
    0.89
     bases
    0.84
    eatures
    0.76
    ategories
    0.76
    HTTP
    0.75
     entirety
    0.75
    Interstitial
    0.72
    ļéĨĴ
    0.72
     gaps
    0.67
     Mellon
    0.63
    Act Density 0.138%

    No Known Activations