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

    Neuronpedia

    INDEX
    Explanations

    references to stairs or ladders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekyll
    -0.70
    FactoryBean
    -0.65
    ıç
    -0.63
     Wadsworth
    -0.62
     getContext
    -0.61
     synapses
    -0.61
    Connie
    -0.61
     Mum
    -0.61
     Huskies
    -0.60
     Jackman
    -0.60
    POSITIVE LOGITS
     ladder
    0.85
     backwards
    0.83
     bleeding
    0.82
     stairs
    0.80
    ladder
    0.79
     Gabel
    0.79
     diving
    0.77
     nahilalakip
    0.77
    MethodManager
    0.76
     Ladder
    0.75
    Act Density 0.109%

    No Known Activations