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

    Neuronpedia

    INDEX
    Explanations

    text announcing and providing information about events or agreements

    oai_token-act-pair · gpt-3.5-turbo

    announcements of company acquisitions or significant updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oan
    -0.74
    ___
    -0.72
     mimic
    -0.71
     pacif
    -0.66
     outwe
    -0.64
     helicop
    -0.64
     overwhel
    -0.63
     alienation
    -0.63
    uman
    -0.63
    irit
    -0.62
    POSITIVE LOGITS
    reetings
    0.91
    LEASE
    0.87
     rejoice
    0.85
     Congratulations
    0.82
     HUGE
    0.81
    CLUS
    0.80
    Volume
    0.80
     festive
    0.77
     announce
    0.76
     refreshed
    0.74
    Act Density 0.586%

    No Known Activations