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

    Neuronpedia

    INDEX
    Explanations

    instances of single quotes and high frequency words indicating a development warning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asts
    -0.17
     Ast
    -0.16
    shaw
    -0.16
    az
    -0.16
     Vide
    -0.15
     az
    -0.15
    wi
    -0.15
     Graves
    -0.15
    azel
    -0.15
    ogan
    -0.14
    POSITIVE LOGITS
    soles
    0.16
    orest
    0.15
    plr
    0.15
    енко
    0.15
    nid
    0.14
    CTX
    0.14
    íĥ
    0.14
    RTOS
    0.14
    .echo
    0.14
     bif
    0.14
    Act Density 0.044%

    No Known Activations