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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sequences or transitions in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.86
     myſelf
    -0.62
    messageInfo
    -0.62
    fromnode
    -0.60
     estekak
    -0.60
    sizeCache
    -0.60
     incrí
    -0.59
     ligiloj
    -0.59
    [@BOS@]
    -0.59
    <unused16>
    -0.59
    POSITIVE LOGITS
     $\
    0.49
     After
    0.46
     Although
    0.46
     If
    0.43
    Although
    0.42
     Though
    0.40
    $\
    0.38
    Though
    0.38
     As
    0.37
    々
    0.36
    Act Density 0.304%

    No Known Activations