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

    Neuronpedia

    INDEX
    Explanations

    references to political processes and interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     He
    -0.47
    He
    -0.46
     Te
    -0.42
    サ
    -0.42
    plotlib
    -0.42
    PECT
    -0.42
    otry
    -0.42
    øy
    -0.42
    BackgroundImage
    -0.42
     Ho
    -0.41
    POSITIVE LOGITS
     '\\;'
    1.03
     ſch
    0.88
     poffible
    0.84
     ſmall
    0.83
     myſelf
    0.82
     ſche
    0.82
     raiſ
    0.81
     pleaſure
    0.79
     ſta
    0.79
     مشين
    0.79
    Act Density 0.867%

    No Known Activations