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

    Neuronpedia

    INDEX
    Explanations

    references to physical hiking trails

    oai_token-act-pair · gpt-3.5-turbo

    references to specific trails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rators
    -0.71
    iation
    -0.70
    ascular
    -0.67
    endiary
    -0.65
    entric
    -0.64
     iod
    -0.64
     Marketable
    -0.63
     automatic
    -0.62
    ately
    -0.61
    ento
    -0.60
    POSITIVE LOGITS
     Blazers
    1.10
     trail
    0.96
    roads
    0.88
     Trail
    0.87
    ways
    0.87
    head
    0.86
    toe
    0.86
    keeper
    0.86
    seeing
    0.84
    gate
    0.82
    Act Density 0.016%

    No Known Activations