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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.95
    <unused3>
    -0.87
    <unused42>
    -0.87
    ̈́
    -0.87
    <unused14>
    -0.87
    <unused8>
    -0.87
    <unused17>
    -0.86
    <unused41>
    -0.86
    <unused16>
    -0.86
    <pad>
    -0.86
    POSITIVE LOGITS
    ,
    0.43
    ;
    0.35
    .
    0.34
    w
    0.32
    behandling
    0.31
     (
    0.31
     None
    0.30
    2
    0.30
    !
    0.29
     and
    0.29
    Act Density 0.193%

    No Known Activations