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

    Neuronpedia

    INDEX
    Explanations

    phrases related to international relationships and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apor
    -0.17
    anc
    -0.16
    peon
    -0.16
    езд
    -0.16
    acob
    -0.15
    875
    -0.15
    erin
    -0.15
    sted
    -0.14
    _bundle
    -0.14
    bows
    -0.14
    POSITIVE LOGITS
    ä½³
    0.17
    HX
    0.15
     Dove
    0.15
     resume
    0.15
    اÙĦب
    0.14
    repr
    0.14
    resume
    0.14
     Resume
    0.14
     Weg
    0.14
     instead
    0.13
    Act Density 0.191%

    No Known Activations