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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political accountability and social relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢод
    -0.16
    бол
    -0.16
    รà¸ģ
    -0.15
    faction
    -0.15
     ho
    -0.15
    amon
    -0.15
    łĢ
    -0.15
    uppe
    -0.14
     lo
    -0.14
    edian
    -0.14
    POSITIVE LOGITS
     mutual
    0.26
     Mutual
    0.22
    between
    0.22
     between
    0.21
     mutually
    0.21
    äºĴ
    0.20
    两人
    0.19
     bilateral
    0.18
    Between
    0.18
     Between
    0.18
    Act Density 0.499%

    No Known Activations