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

    Neuronpedia

    INDEX
    Explanations

    terms related to generations or new versions of products

    oai_token-act-pair · gpt-3.5-turbo

    references to different generations of technology or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.91
    DAY
    -0.89
    amina
    -0.87
    phy
    -0.71
    orial
    -0.69
    prus
    -0.68
    amen
    -0.68
    Hour
    -0.67
    esar
    -0.67
    anson
    -0.66
    POSITIVE LOGITS
     iteration
    1.02
     incarnation
    0.87
     versions
    0.82
     consoles
    0.82
     batch
    0.81
     technologies
    0.81
     version
    0.80
     installment
    0.79
     chipset
    0.77
     architectures
    0.76
    Act Density 0.077%

    No Known Activations