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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    processes and actions related to assembly and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Samar
    -0.89
    ONSORED
    -0.83
     Paran
    -0.75
     Fatal
    -0.75
    ¥µ
    -0.71
     Pension
    -0.69
     Incarn
    -0.69
    天
    -0.69
     Empires
    -0.68
     Mirage
    -0.67
    POSITIVE LOGITS
     adhesive
    1.01
     thickness
    0.95
     silicone
    0.94
     diameter
    0.94
     acrylic
    0.93
     attachment
    0.91
     molded
    0.90
     glue
    0.88
     filament
    0.87
     holes
    0.86
    Act Density 0.297%

    No Known Activations