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

    Neuronpedia

    INDEX
    Explanations

    the word "merely" and its instances in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PLUS
    -0.75
    ibal
    -0.69
    clusively
    -0.66
    vals
    -0.65
     Definitely
    -0.63
     Plus
    -0.63
     Nurs
    -0.62
     Also
    -0.60
    affer
    -0.60
     Cursed
    -0.59
    POSITIVE LOGITS
    ifiable
    0.83
     incidental
    0.82
     mortals
    0.79
     cosmetic
    0.79
     superficial
    0.78
     inconven
    0.78
    clair
    0.76
     guiActiveUn
    0.74
     guiIcon
    0.70
    rical
    0.69
    Act Density 0.011%

    No Known Activations