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

    Neuronpedia

    INDEX
    Explanations

    concepts related to blessings and positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vet
    -0.51
    ams
    -0.51
    osh
    -0.49
    idste
    -0.48
    OSH
    -0.45
     Bad
    -0.45
     Sr
    -0.45
     Vasquez
    -0.45
    ct
    -0.44
    ↵
    -0.43
    POSITIVE LOGITS
     ſche
    0.67
    SharedDtor
    0.65
    AndEndTag
    0.65
     للمعارف
    0.62
    ſelves
    0.61
    ſelf
    0.60
    RenderAtEndOf
    0.58
    出版年
    0.58
    InitVars
    0.57
    ientras
    0.57
    Act Density 0.283%

    No Known Activations