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

    Neuronpedia

    INDEX
    Explanations

    references to trails or pathways

    oai_token-act-pair · gpt-3.5-turbo

    references to hiking trails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     automatic
    -0.70
    rators
    -0.67
     Marketable
    -0.65
    ento
    -0.64
    ately
    -0.63
    ascular
    -0.62
     palp
    -0.62
    orporated
    -0.61
    endiary
    -0.61
    iation
    -0.60
    POSITIVE LOGITS
     Blazers
    1.10
     trail
    0.97
    ways
    0.89
    walker
    0.88
    keeper
    0.88
    gate
    0.86
    opa
    0.85
    finding
    0.85
    seeing
    0.84
    bl
    0.83
    Act Density 0.022%

    No Known Activations