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

    Neuronpedia

    INDEX
    Explanations

    Proper names and affiliations of entities, potentially related to a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to the Muppets or related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GW
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
     willful
    -0.72
    76561
    -0.69
    å°Ĩ
    -0.68
     logger
    -0.67
     corrosion
    -0.67
     dissolution
    -0.65
    binding
    -0.64
     frustration
    -0.63
    POSITIVE LOGITS
    ortun
    1.16
    olicy
    1.12
    sburgh
    1.11
    enhagen
    1.09
    enthal
    1.03
    etry
    1.02
    esy
    0.99
    onent
    0.99
    ete
    0.98
    odcast
    0.95
    Act Density 0.007%

    No Known Activations