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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disagreement and conflict, particularly in the context of political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.62
    (")");
    -0.61
     ").
    -0.60
     Fong
    -0.55
    virons
    -0.55
    nius
    -0.53
    صد
    -0.53
    onian
    -0.52
     EdgeInsets
    -0.52
    みると
    -0.52
    POSITIVE LOGITS
     you
    0.93
    \{\\
    0.87
     me
    0.86
     resourceCulture
    0.81
     us
    0.75
     yours
    0.74
     him
    0.71
     your
    0.71
     them
    0.70
    +#+#
    0.66
    Act Density 0.424%

    No Known Activations