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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Spanish words/phrases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    .</
    -0.71
    $.
    -0.70
    .''
    -0.65
    ".
    -0.65
    )."
    -0.62
    .).
    -0.62
    .�
    -0.62
    *.
    -0.61
    ).
    -0.61
     ..."
    -0.59
    POSITIVE LOGITS
     meanwhile
    0.75
    ouple
    0.53
    ccording
    0.51
     spokesman
    0.51
     spokeswoman
    0.48
    udos
    0.47
    surprisingly
    0.47
     Variant
    0.46
    prisingly
    0.44
     tweeted
    0.44
    Act Density 1.197%

    No Known Activations