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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interference or disruption

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interference or interruption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phans
    -0.72
     Survivors
    -0.67
     Rats
    -0.64
     Lazarus
    -0.64
     cents
    -0.62
    inguished
    -0.61
    culosis
    -0.60
     Canaver
    -0.59
    mary
    -0.59
     Schwar
    -0.59
    POSITIVE LOGITS
     airflow
    0.84
     lawful
    0.81
     flow
    0.80
     movements
    0.77
     transmissions
    0.76
     messenger
    0.74
     proceedings
    0.71
     traffic
    0.71
     delivery
    0.71
     doorway
    0.70
    Act Density 0.425%

    No Known Activations