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

    Neuronpedia

    INDEX
    Explanations

    political figures and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate criticisms or conflicts involving public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     %%
    -0.79
     {:
    -0.79
     âĶľâĶĢâĶĢ
    -0.71
     :=
    -0.70
     Cf
    -0.70
    "}],"
    -0.68
     âĨij
    -0.68
    ··
    -0.67
    byss
    -0.65
    _.
    -0.65
    POSITIVE LOGITS
     Donald
    1.02
     his
    0.96
     embattled
    0.94
     presumptive
    0.92
     himself
    0.88
     controversial
    0.87
     MSNBC
    0.85
     Republican
    0.82
     Hillary
    0.81
     apologizing
    0.81
    Act Density 0.744%

    No Known Activations