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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific events or incidents, possibly involving locations or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social and systemic issues affecting communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dyl
    -0.85
    etsk
    -0.79
    catentry
    -0.73
    akings
    -0.73
    vern
    -0.72
    cms
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    ipl
    -0.69
    auth
    -0.68
    nob
    -0.67
    POSITIVE LOGITS
     Them
    0.96
     Relationship
    0.94
     Ones
    0.93
     Replacement
    0.93
     Guys
    0.91
     Than
    0.91
     Himself
    0.90
     Based
    0.88
     Donation
    0.88
     Him
    0.87
    Act Density 0.513%

    No Known Activations