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

    Neuronpedia

    INDEX
    Explanations

    references to time, particularly the word "ago."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    autant
    -0.85
    aarrggbb
    -0.68
    stantial
    -0.67
    этому
    -0.65
    unus
    -0.65
    '.$
    -0.63
     Lilli
    -0.62
    czegó
    -0.61
    '),
    -0.61
     franca
    -0.61
    POSITIVE LOGITS
     ago
    1.17
     Ago
    0.77
     AGO
    0.76
     виправивши
    0.74
     gynhyrchwyd
    0.70
    CrossRef
    0.70
    Ago
    0.67
     Ayer
    0.66
     sofas
    0.65
    VersionUID
    0.65
    Act Density 0.047%

    No Known Activations