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

    Neuronpedia

    INDEX
    Explanations

    phrases related to third-party interactions and data sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.58
     wipers
    -0.54
    eroll
    -0.54
     Vorstand
    -0.54
    achet
    -0.53
     roo
    -0.53
     foncé
    -0.53
    avaş
    -0.52
     papy
    -0.52
    Filmografie
    -0.51
    POSITIVE LOGITS
     outside
    0.74
    osoba
    0.70
     يتيمه
    0.64
    outside
    0.62
    ########.
    0.59
     Outside
    0.59
     fremden
    0.58
    Outside
    0.57
    Rohy
    0.56
     OUTSIDE
    0.56
    Act Density 0.333%

    No Known Activations