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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to the removal or abolishment of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.74
    akening
    -0.69
    felt
    -0.64
    rings
    -0.64
    enegger
    -0.62
    eur
    -0.62
    fab
    -0.61
    ETF
    -0.61
    here
    -0.61
    NG
    -0.61
    POSITIVE LOGITS
    aneous
    0.94
    aneously
    0.78
    noxious
    0.76
     duplication
    0.76
    inators
    0.74
    ministic
    0.73
     redund
    0.69
    ication
    0.68
     needless
    0.67
     distractions
    0.66
    Act Density 0.040%

    No Known Activations