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

    Neuronpedia

    INDEX
    Explanations

    words indicating growth or increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hosting
    -0.52
     hosting
    -0.49
     journaling
    -0.49
    AsUp
    -0.48
    Hosting
    -0.48
    bosity
    -0.46
     ſche
    -0.45
     spacer
    -0.45
     hitch
    -0.45
    TagHelpers
    -0.45
    POSITIVE LOGITS
     increasing
    2.08
     decreasing
    1.92
     rising
    1.91
    Increasing
    1.88
    increasing
    1.85
     Increasing
    1.84
     growing
    1.82
     declining
    1.76
     expanding
    1.74
    decreasing
    1.64
    Act Density 0.322%

    No Known Activations