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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related patterns

    oai_token-act-pair · gpt-3.5-turbo

    frequency or occurrence of punctuation and certain phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.37
    yip
    -0.37
     [|
    -0.36
    romeda
    -0.35
     grooming
    -0.35
    */
    -0.35
     handshake
    -0.34
     */
    -0.33
    Downloadha
    -0.33
     conflic
    -0.33
    POSITIVE LOGITS
    ãĥķãĤ©
    0.38
    gov
    0.36
    conom
    0.34
    RNA
    0.34
    sylv
    0.34
    ochet
    0.32
    ologic
    0.32
    ãĥĻ
    0.31
    cade
    0.31
    annabin
    0.31
    Act Density 2.940%

    No Known Activations