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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical values and relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classifications and categories, particularly those associated with structure and type

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.75
     prom
    -0.72
     constellation
    -0.70
     disg
    -0.69
     tremend
    -0.69
    amac
    -0.69
    ayn
    -0.68
     regul
    -0.68
     cig
    -0.68
    istine
    -0.64
    POSITIVE LOGITS
     Decay
    1.13
     Aging
    0.94
     Emails
    0.85
     Profile
    0.83
     Quote
    0.82
    wise
    0.81
    Space
    0.80
    Ey
    0.80
    Track
    0.79
     Shots
    0.78
    Act Density 0.260%

    No Known Activations