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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions and capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eſ
    -0.68
     whoſe
    -0.68
     ſche
    -0.67
     pleaſure
    -0.65
     myſelf
    -0.64
     iſt
    -0.62
     dieß
    -0.61
     giebt
    -0.61
     ſeveral
    -0.60
     itſelf
    -0.59
    POSITIVE LOGITS
    QMetaType
    0.74
    +#+#
    0.74
    gatsby
    0.68
     intptr
    0.66
    nestjs
    0.64
    EndProject
    0.64
     <=",
    0.64
    IntoConstraints
    0.62
     ISNI
    0.62
     المعيارى
    0.62
    Act Density 0.152%

    No Known Activations