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

    Neuronpedia

    INDEX
    Explanations

    sequences of text separated by a specific symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igi
    -0.64
    aeda
    -0.61
    ardless
    -0.57
     endeavour
    -0.56
     legally
    -0.56
    ividual
    -0.56
    nesday
    -0.55
     equival
    -0.55
    uese
    -0.55
    ibrary
    -0.55
    POSITIVE LOGITS
    ccording
    0.82
    Posted
    0.73
    CVE
    0.73
    SPONSORED
    0.72
    However
    0.72
    Newsletter
    0.71
    ³³³³
    0.71
    Filename
    0.71
    RESULTS
    0.71
    Commercial
    0.70
    Act Density 1.099%

    No Known Activations