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

    Neuronpedia

    INDEX
    Explanations

    references to positions and roles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĪ
    -0.17
     nackte
    -0.16
    698
    -0.16
    anga
    -0.15
    stanbul
    -0.14
    723
    -0.14
    imb
    -0.14
     bol
    -0.14
    borg
    -0.13
    ensa
    -0.13
    POSITIVE LOGITS
    arius
    0.21
     society
    0.17
     ฿
    0.16
    ville
    0.15
     niche
    0.15
    arger
    0.15
    ertype
    0.15
    tright
    0.14
    among
    0.14
     among
    0.14
    Act Density 0.160%

    No Known Activations