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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and their variations in size and age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -0.79
     Z
    -0.75
     mit
    -0.74
     j
    -0.73
     J
    -0.71
     k
    -0.71
     Man
    -0.68
     l
    -0.67
     Get
    -0.67
     f
    -0.66
    POSITIVE LOGITS
     leſs
    1.69
     myſelf
    1.67
     itſelf
    1.51
     pleaſure
    1.44
     himſelf
    1.41
     Anſ
    1.41
     greateſt
    1.40
     Jefus
    1.36
     Majefty
    1.36
    ſelves
    1.35
    Act Density 0.157%

    No Known Activations