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

    Neuronpedia

    INDEX
    Explanations

    security-related terms or financial figures

    oai_token-act-pair · gpt-3.5-turbo

    references to financial figures and security-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutshell
    -0.69
     widest
    -0.69
    gest
    -0.66
    gger
    -0.65
    ãĥ´
    -0.64
    EStream
    -0.64
    inventoryQuantity
    -0.63
    apest
    -0.63
    Gra
    -0.63
     Lifetime
    -0.62
    POSITIVE LOGITS
     layers
    0.88
    iations
    0.84
     than
    0.84
     arrivals
    0.83
    than
    0.80
    ricular
    0.77
     additions
    0.77
     added
    0.76
     baggage
    0.75
    erous
    0.71
    Act Density 0.196%

    No Known Activations