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

    Neuronpedia

    INDEX
    Explanations

    words and phrases describing persistence and harshness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ataires
    -0.17
    .TIM
    -0.15
    λÏī
    -0.15
    bos
    -0.15
    adel
    -0.15
    ffer
    -0.15
    rax
    -0.14
    CLAIM
    -0.14
    (Collision
    -0.14
    Occurred
    -0.14
    POSITIVE LOGITS
    ently
    0.17
    ingly
    0.16
     Kahn
    0.15
    uly
    0.15
    Ñī
    0.15
    ouser
    0.15
    çļĦãģ«
    0.14
    ÑģÑĥÑĤ
    0.14
    .DropTable
    0.14
     Drive
    0.14
    Act Density 0.027%

    No Known Activations