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

    Neuronpedia

    INDEX
    Explanations

    recurring adverbs that indicate frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     always
    -0.90
     generally
    -0.83
     mostly
    -0.82
     sempre
    -0.82
     usually
    -0.79
     everytime
    -0.78
    always
    -0.77
     siempre
    -0.76
     typically
    -0.76
     everywhere
    -0.76
    POSITIVE LOGITS
     simply
    0.83
     бывает
    0.83
     downright
    0.81
     simplemente
    0.78
    simply
    0.77
    times
    0.77
     times
    0.76
    甚至是
    0.74
    干脆
    0.73
    Simply
    0.72
    Act Density 0.546%

    No Known Activations