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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instances of measurement or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombok
    -0.18
    _:*
    -0.15
    бÑĢа
    -0.14
    çħ§
    -0.14
     BÄ°L
    -0.14
    xBA
    -0.13
     Became
    -0.13
    iÅŁtir
    -0.13
    470
    -0.13
     HEAP
    -0.13
    POSITIVE LOGITS
     had
    1.10
    had
    1.02
    Had
    0.94
     Had
    0.91
     hade
    0.71
     habÃŃa
    0.69
     hatte
    0.69
     avait
    0.63
     hadde
    0.63
     hadn
    0.59
    Act Density 0.536%

    No Known Activations