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

    Neuronpedia

    INDEX
    Explanations

    geographic locations and their associated movements or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athom
    -0.15
    vertise
    -0.15
    arella
    -0.15
     Staten
    -0.14
    944
    -0.14
     Buff
    -0.14
    ROT
    -0.13
     Opr
    -0.13
    aria
    -0.13
    boo
    -0.13
    POSITIVE LOGITS
     Bend
    0.23
     Eugene
    0.23
     Rent
    0.23
     Wen
    0.20
     Grants
    0.19
     Fallon
    0.19
     Iss
    0.18
    Rent
    0.18
     Yak
    0.18
     Moses
    0.18
    Act Density 0.119%

    No Known Activations