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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to server connections and file paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     takson
    -0.14
     Brit
    -0.14
    turnstile
    -0.14
    "struct
    -0.14
     ÙĨاÙħÙĩ
    -0.13
    'gc
    -0.13
    оÑĢи
    -0.13
    mpi
    -0.13
     Boeh
    -0.13
    WEBPACK
    -0.13
    POSITIVE LOGITS
    254
    0.33
    168
    0.22
    255
    0.22
     addresses
    0.20
    172
    0.20
    252
    0.19
     address
    0.19
    192
    0.18
    169
    0.18
    248
    0.18
    Act Density 0.009%

    No Known Activations