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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    end up state or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auroit
    -0.65
     feroit
    -0.64
    guiente
    -0.62
     čierna
    -0.60
     niega
    -0.59
    ientras
    -0.59
     ainfi
    -0.57
     própri
    -0.57
     bluzka
    -0.56
     zimowa
    -0.56
    POSITIVE LOGITS
     stuck
    0.54
     embro
    0.52
     getResult
    0.52
     up
    0.50
     traum
    0.50
    pshot
    0.49
     entangled
    0.48
     involved
    0.48
     out
    0.47
     rep
    0.47
    Act Density 0.005%

    No Known Activations