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

    Neuronpedia

    INDEX
    Explanations

    references to crossing or traversing various geographical or metaphorical boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    735
    -0.15
     Hoch
    -0.15
    isha
    -0.15
    resi
    -0.15
    icia
    -0.15
    rani
    -0.14
    BackStack
    -0.14
     dig
    -0.14
    iffe
    -0.14
    737
    -0.14
    POSITIVE LOGITS
     Crossing
    0.26
    -cross
    0.25
     crossing
    0.24
     bridge
    0.23
     crossings
    0.23
     into
    0.22
     bridges
    0.20
    cross
    0.20
     crossed
    0.20
     Swords
    0.20
    Act Density 0.045%

    No Known Activations