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

    Neuronpedia

    INDEX
    Explanations

    interviews or interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating communication or interaction with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ashore
    -0.77
    wcsstore
    -0.75
    void
    -0.74
    -|
    -0.71
    borgh
    -0.71
    coming
    -0.70
    ogging
    -0.70
    ther
    -0.68
    atra
    -0.68
    Interstitial
    -0.68
    POSITIVE LOGITS
     representatives
    1.09
     executives
    0.92
     him
    0.91
     witnesses
    0.90
     experts
    0.89
     stakeholders
    0.86
     editors
    0.85
     sources
    0.84
     insiders
    0.83
     lawyers
    0.80
    Act Density 0.151%

    No Known Activations