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

    Neuronpedia

    INDEX
    Explanations

    occurrences of geographical locations or directional references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssp
    -0.18
    ilihan
    -0.15
     geg
    -0.15
    ieve
    -0.14
    itud
    -0.14
    ecs
    -0.14
    iveness
    -0.14
    çek
    -0.14
    spm
    -0.14
    agine
    -0.13
    POSITIVE LOGITS
    most
    0.18
    gger
    0.17
    /left
    0.16
    -most
    0.16
    quil
    0.14
    ãĥ¯ãĤ¤ãĥĪ
    0.14
    oser
    0.14
     Death
    0.14
    æŀ
    0.13
    enen
    0.13
    Act Density 0.031%

    No Known Activations