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

    Neuronpedia

    INDEX
    Explanations

    references to physical or structural components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.57
    h
    -0.54
    aa
    -0.53
    c
    -0.50
    S
    -0.50
    a
    -0.48
    es
    -0.48
    b
    -0.47
    f
    -0.47
    Con
    -0.47
    POSITIVE LOGITS
     kaarangay
    1.08
     myſelf
    1.05
    COMPONENT
    0.99
    WebVitals
    0.98
     Component
    0.95
     themſelves
    0.95
     COMPONENT
    0.90
    enumi
    0.89
     component
    0.88
    component
    0.88
    Act Density 0.147%

    No Known Activations