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

    Neuronpedia

    INDEX
    Explanations

    repeated expressions of frequency or habit

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

    the word "often" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.56
     autorytatywna
    -0.52
     '\\;'
    -0.50
     يتيمه
    -0.48
    ddots
    -0.48
    WebpackPlugin
    -0.47
    wapV
    -0.47
     Limb
    -0.47
     continuity
    -0.47
    始终
    -0.47
    POSITIVE LOGITS
     times
    0.79
    times
    0.74
     genug
    0.65
     TIMES
    0.56
    Times
    0.56
     vezes
    0.54
     бывает
    0.52
     enough
    0.51
     čast
    0.50
     xuyên
    0.50
    Act Density 0.103%

    No Known Activations