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

    Neuronpedia

    INDEX
    Explanations

    names of locations or groups related to a specific region or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular group or entity within a specific context, particularly related to names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Luthor
    -0.73
     Luther
    -0.69
    ãĤ¹ãĥĪ
    -0.68
     exorc
    -0.61
     TRANS
    -0.61
    matter
    -0.61
     steroids
    -0.61
     infiltrate
    -0.59
     VK
    -0.59
     Mayhem
    -0.58
    POSITIVE LOGITS
    esome
    1.51
    akening
    1.40
    aii
    1.21
    yer
    1.11
    akens
    1.07
    ashington
    1.06
    kward
    1.06
    orld
    1.05
    amba
    1.03
    orks
    1.03
    Act Density 0.043%

    No Known Activations