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

    Neuronpedia

    INDEX
    Explanations

    expressions of anger or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions, particularly rants and tirades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.96
    earances
    -0.77
     acquisitions
    -0.75
    licts
    -0.71
    prus
    -0.69
    emale
    -0.68
    phis
    -0.66
    metics
    -0.65
    ppo
    -0.64
    rity
    -0.63
    POSITIVE LOGITS
     tir
    1.00
     rant
    0.95
     aloud
    0.86
     loudly
    0.81
     spew
    0.74
     angrily
    0.73
     against
    0.73
     louder
    0.72
     goodbye
    0.72
     uttered
    0.70
    Act Density 0.038%

    No Known Activations