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

    Neuronpedia

    INDEX
    Explanations

    words related to problems or challenges

    oai_token-act-pair · gpt-3.5-turbo

    references to various problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oliberal
    -0.87
    sonian
    -0.73
    ilings
    -0.70
    ctors
    -0.69
    rica
    -0.67
    ramid
    -0.66
    zie
    -0.66
    tsky
    -0.65
    issors
    -0.65
    ãĥ£
    -0.65
    POSITIVE LOGITS
     plag
    1.19
    hooting
    1.17
     caused
    1.01
     encountered
    1.00
     arise
    0.95
     affecting
    0.95
     plagued
    0.95
     relating
    0.92
     arising
    0.91
     resolved
    0.91
    Act Density 0.163%

    No Known Activations