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

    Neuronpedia

    INDEX
    Explanations

    references to nature and outdoor attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    şört
    -0.36
    :✨
    -0.35
    comuna
    -0.35
    apropri
    -0.33
     گران
    -0.33
     Geistes
    -0.31
    columnNumber
    -0.31
     lakier
    -0.30
     Lightboxes
    -0.30
    ivably
    -0.30
    POSITIVE LOGITS
     surla
    0.79
    +#+
    0.59
     honeymoon
    0.58
     resorts
    0.57
     sightseeing
    0.56
     tourist
    0.56
     ModelRenderer
    0.55
    ☸
    0.54
     Tourist
    0.54
     Honeymoon
    0.54
    Act Density 0.116%

    No Known Activations