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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate communication or expression of opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     motions
    -0.67
     submitting
    -0.65
     withdrew
    -0.64
     withdraw
    -0.63
     Meet
    -0.61
     deletion
    -0.61
     filing
    -0.61
     discuss
    -0.60
     withdrawn
    -0.60
     mailing
    -0.59
    POSITIVE LOGITS
     tremend
    0.83
    ãĥĺãĥ©
    0.82
    emi
    0.81
    itivity
    0.79
    geon
    0.77
    ends
    0.75
    paralle
    0.72
    rises
    0.71
    riz
    0.71
     volumes
    0.70
    Act Density 0.211%

    No Known Activations