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

    Neuronpedia

    INDEX
    Explanations

    explanations of processes or mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.16
    ina
    -0.15
    uder
    -0.15
    INA
    -0.14
    raud
    -0.14
    loor
    -0.14
    inee
    -0.14
    INE
    -0.14
     Crash
    -0.13
    ÑĪÑĥ
    -0.13
    POSITIVE LOGITS
     Basically
    0.18
     Simply
    0.17
     basically
    0.17
    ãģ¾ãģļ
    0.17
    Basically
    0.16
    Brief
    0.16
     simply
    0.16
     consist
    0.15
    unlink
    0.15
     Brief
    0.15
    Act Density 0.312%

    No Known Activations