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

    Neuronpedia

    INDEX
    Explanations

    comparatively strong entities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of strength or being stronger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolley
    -0.87
    pty
    -0.84
    ourn
    -0.68
     Newly
    -0.68
    mits
    -0.68
    mberg
    -0.68
    adr
    -0.67
     Lyons
    -0.66
     Roche
    -0.66
    ffe
    -0.66
    POSITIVE LOGITS
     streng
    1.08
     referen
    1.02
     veter
    0.98
     stronger
    0.97
     advoc
    0.94
     strength
    0.94
     weaker
    0.91
     tremend
    0.90
     undermin
    0.89
     behavi
    0.88
    Act Density 0.008%

    No Known Activations