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

    Neuronpedia

    INDEX
    Explanations

    references to political events or scandals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ")).
    -0.51
    ")));
    -0.49
    رشف
    -0.49
    ())).
    -0.48
     "));
    -0.48
    autique
    -0.46
     }).
    -0.46
    ))).
    -0.46
    "]').
    -0.46
    __":
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.90
    WriteBarrier
    0.89
     كومونز
    0.82
     houſe
    0.80
     itſelf
    0.80
    Geplaatst
    0.78
    IntoConstraints
    0.74
    клопе
    0.73
     ſever
    0.72
     Theſe
    0.70
    Act Density 1.124%

    No Known Activations