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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the abbreviation "CP" followed by a letter or number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific polling or survey organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gie
    -0.74
    gaard
    -0.73
    sbm
    -0.73
     Admir
    -0.72
    âĸ¬
    -0.66
    combe
    -0.66
    ificant
    -0.65
    ebted
    -0.65
    lia
    -0.64
    iyah
    -0.63
    POSITIVE LOGITS
    odcast
    1.17
    ublic
    1.14
    olicy
    1.13
    ixel
    1.09
    rint
    1.07
    ython
    1.04
    rompt
    1.01
    ossible
    1.01
    etition
    1.01
    EG
    1.01
    Act Density 0.048%

    No Known Activations