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

    Neuronpedia

    INDEX
    Explanations

    terms related to disruption and interruption

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

    terms related to disruption and interruption

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    phans
    -0.78
    uncle
    -0.71
    ocene
    -0.66
    eah
    -0.66
    bold
    -0.64
    rahim
    -0.64
    hl
    -0.63
    reed
    -0.62
    fetched
    -0.61
    silver
    -0.61
    POSITIVE LOGITS
     disrupted
    0.96
     disruptions
    0.82
     disrupt
    0.79
     disruptive
    0.78
     curfew
    0.78
     disrupting
    0.76
    ions
    0.73
    ²¾
    0.72
     interrupts
    0.72
    ĵĺ
    0.72
    Act Density 0.094%

    No Known Activations