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

    Neuronpedia

    INDEX
    Explanations

    references to sharing content on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ragaz
    -0.17
    elf
    -0.16
    ium
    -0.15
    liers
    -0.15
    ense
    -0.15
    ehr
    -0.15
    strain
    -0.14
    ee
    -0.14
    eh
    -0.14
     Hij
    -0.14
    POSITIVE LOGITS
    ARGV
    0.16
    -pills
    0.15
    ]={↵
    0.14
    arty
    0.14
    MBED
    0.14
    ulta
    0.14
    weathermap
    0.14
    озÑĸ
    0.14
    edad
    0.14
    zer
    0.13
    Act Density 0.029%

    No Known Activations