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

    Neuronpedia

    INDEX
    Explanations

    mention of geographic locations and wilderness-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hill
    -0.24
     hills
    -0.21
     Hills
    -0.20
     Hill
    -0.20
    hill
    -0.19
    ä¸ĺ
    -0.18
     hil
    -0.18
     mound
    -0.17
    eor
    -0.16
    kil
    -0.15
    POSITIVE LOGITS
     Tato
    0.16
    è¼
    0.16
     switch
    0.15
    ικ
    0.15
     forks
    0.15
     NFS
    0.15
    iteration
    0.15
     Hai
    0.15
     Cathedral
    0.15
    TRACE
    0.15
    Act Density 0.037%

    No Known Activations