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

    Neuronpedia

    INDEX
    Explanations

    instances of opinionated or critical commentary regarding events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nen
    -0.16
    uniq
    -0.15
     Rif
    -0.15
    anes
    -0.14
    ãĤ¸ãĤª
    -0.14
    ltk
    -0.14
     tendency
    -0.14
    incerely
    -0.14
    uent
    -0.14
    ·æĸ°
    -0.14
    POSITIVE LOGITS
     transformed
    0.24
     recognizable
    0.22
    recogn
    0.22
     recogn
    0.21
    Transform
    0.21
     transforms
    0.20
     transform
    0.20
    transform
    0.20
    -transform
    0.19
     completely
    0.19
    Act Density 0.141%

    No Known Activations