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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suggestions and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.15
     mankind
    -0.15
    indle
    -0.14
    ziehung
    -0.14
    gamber
    -0.14
    ruba
    -0.14
     prive
    -0.14
     [@
    -0.13
    Ticks
    -0.13
    ohl
    -0.13
    POSITIVE LOGITS
     get
    0.18
     go
    0.17
    åª
    0.16
     went
    0.15
    acro
    0.14
    æ¥
    0.14
     finished
    0.14
     stay
    0.14
     gone
    0.14
     Go
    0.14
    Act Density 0.965%

    No Known Activations