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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical strength and robustness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to durability and resilience of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPA
    -0.83
    riber
    -0.80
    atorium
    -0.80
    urger
    -0.78
    liga
    -0.77
    atri
    -0.76
    vertis
    -0.76
    ulhu
    -0.73
    yrinth
    -0.73
    inburgh
    -0.72
    POSITIVE LOGITS
    nesses
    0.86
     resilience
    0.85
     resilient
    0.84
     durability
    0.79
     brittle
    0.77
     inver
    0.77
    theless
    0.76
     fragile
    0.75
     absor
    0.74
     plastics
    0.73
    Act Density 0.083%

    No Known Activations