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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     has
    -0.56
     seems
    -0.50
    has
    -0.48
     Has
    -0.44
     lately
    -0.42
     HAS
    -0.41
    Has
    -0.39
    seems
    -0.39
     is
    -0.37
     scheint
    -0.37
    POSITIVE LOGITS
     hubiera
    1.11
     hubieran
    1.03
     hubiese
    0.96
     auraient
    0.90
     aurait
    0.86
     hätte
    0.85
     habrían
    0.84
     eût
    0.81
     hätten
    0.80
     avrebbero
    0.76
    Act Density 0.362%

    No Known Activations