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

    Neuronpedia

    INDEX
    Explanations

    words related to technical operations and configurations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to processes and systems in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iott
    -0.77
    sa
    -0.73
    ties
    -0.73
    quart
    -0.68
    QB
    -0.67
    yon
    -0.65
    vu
    -0.65
    eva
    -0.65
    si
    -0.64
    âĢ²
    -0.64
    POSITIVE LOGITS
    redients
    1.00
    HAM
    0.90
    tons
    0.84
     spree
    0.78
     techniques
    0.78
     rituals
    0.75
     ceremonies
    0.74
     torches
    0.74
     prowess
    0.70
     conventions
    0.68
    Act Density 0.208%

    No Known Activations