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

    Neuronpedia

    INDEX
    Explanations

    the word "most" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    �
    -0.84
    stice
    -0.76
    layer
    -0.70
    iseum
    -0.69
    wagen
    -0.69
    urity
    -0.64
    uler
    -0.64
     Morse
    -0.64
    iku
    -0.63
    agher
    -0.63
    POSITIVE LOGITS
     recent
    0.82
     likely
    0.74
     Recent
    0.72
     Wanted
    0.69
     probable
    0.67
     recently
    0.66
     Popular
    0.66
     preferably
    0.66
     often
    0.65
     prevalent
    0.65
    Act Density 0.034%

    No Known Activations