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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing a statement or point

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħ
    -0.74
    ications
    -0.71
    utical
    -0.68
    acers
    -0.68
    Ĵ
    -0.68
    Ľ
    -0.68
    320
    -0.68
    arest
    -0.67
    BuyableInstoreAndOnline
    -0.67
    ARS
    -0.66
    POSITIVE LOGITS
     week
    0.93
     trope
    0.90
     arrangement
    0.89
     discrepancy
    0.87
     tactic
    0.85
     phenomenon
    0.83
     latest
    0.82
     particular
    0.79
     guy
    0.79
     happening
    0.78
    Act Density 0.130%

    No Known Activations