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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "until" and its variations

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

    "until" followed by a pronoun or determiner

    np_acts-logits-general · gemini-2.0-flash

    until after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.05
    ſelves
    -0.88
    ſelf
    -0.87
     ſever
    -0.83
     Efq
    -0.82
     Monfieur
    -0.82
    Tikang
    -0.82
     Majefty
    -0.82
     Anſ
    -0.80
     purpoſe
    -0.79
    POSITIVE LOGITS
     we
    1.23
     they
    1.19
     the
    1.11
     you
    1.11
     he
    0.97
     there
    0.94
     it
    0.91
     someone
    0.79
     
    0.74
     I
    0.74
    Act Density 0.242%

    No Known Activations