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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversies and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political scandals and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''.
    -0.66
    >.
    -0.58
    anwhile
    -0.57
     '.
    -0.56
    `.
    -0.56
    .�
    -0.54
    .}
    -0.51
    "!
    -0.51
    $.
    -0.50
    .''
    -0.48
    POSITIVE LOGITS
    ,[
    1.03
    ?,
    1.02
     (),
    0.91
    !,
    0.89
    ,
    0.86
    *,
    0.85
     ,
    0.85
    +,
    0.83
    ®,
    0.82
    %,
    0.79
    Act Density 1.652%

    No Known Activations