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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations, particularly islands and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udit
    -0.18
    ãĥ¼ãĤº
    -0.16
    razil
    -0.16
     mesh
    -0.16
    tul
    -0.15
    ÌĨ
    -0.15
     mex
    -0.14
     ConnectionState
    -0.14
     Twist
    -0.14
    pack
    -0.13
    POSITIVE LOGITS
     Canary
    0.23
     Las
    0.18
     Made
    0.17
    Made
    0.17
     Fu
    0.17
    icode
    0.15
    .vm
    0.15
    fifo
    0.15
     Mao
    0.15
     Hier
    0.15
    Act Density 0.012%

    No Known Activations