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

    Neuronpedia

    INDEX
    Explanations

    references to errors or mistreatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anness
    -0.16
    è¼
    -0.15
     Kraft
    -0.15
    arsity
    -0.15
    ieren
    -0.15
    zig
    -0.15
    rices
    -0.15
     kus
    -0.14
    pany
    -0.14
    dish
    -0.14
    POSITIVE LOGITS
    reatment
    0.33
    resses
    0.30
    ubishi
    0.28
    ake
    0.27
    aken
    0.27
    akes
    0.27
    ral
    0.26
    reated
    0.24
    AKE
    0.24
    y
    0.23
    Act Density 0.010%

    No Known Activations