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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "come."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IContainer
    -0.82
    degrad
    -0.65
     Bettina
    -0.65
    zert
    -0.64
    zern
    -0.63
    nyder
    -0.61
    <sup>
    -0.60
     Gr
    -0.60
     Leach
    -0.59
    ContextHolder
    -0.59
    POSITIVE LOGITS
    Comes
    1.09
    COMES
    1.03
    Came
    1.00
     Comes
    1.00
     COME
    0.98
     comes
    0.98
     cometh
    0.97
     COMES
    0.96
    comes
    0.95
     Came
    0.91
    Act Density 0.093%

    No Known Activations