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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain punctuation-related tokens or are focused on upward movements and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UObject
    -0.15
    raj
    -0.15
     Animalia
    -0.14
    267
    -0.14
     lagi
    -0.14
    iones
    -0.14
    enes
    -0.14
    견
    -0.14
    нка
    -0.13
    æŦ
    -0.13
    POSITIVE LOGITS
    yme
    0.16
    udic
    0.16
    obl
    0.14
     Sean
    0.14
    ohan
    0.14
    abo
    0.13
    ÑİÑĤ
    0.13
    ego
    0.13
    .createObject
    0.13
    te
    0.13
    Act Density 0.007%

    No Known Activations