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

    Neuronpedia

    INDEX
    Explanations

    common phrases and structures indicative of questions or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤаÑĢ
    -0.19
    transparent
    -0.16
    weg
    -0.15
     Duc
    -0.14
     neutral
    -0.14
     Dre
    -0.14
    ARY
    -0.14
    Parm
    -0.14
    ิà¸ķร
    -0.14
     transparent
    -0.14
    POSITIVE LOGITS
     Verd
    0.15
    ियत
    0.15
    ject
    0.15
     thụ
    0.15
    vvm
    0.15
    åħģ
    0.15
    ä¸ĢæŃ¥
    0.14
    ooke
    0.14
     nomine
    0.14
    UNUSED
    0.14
    Act Density 0.007%

    No Known Activations