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

    Neuronpedia

    INDEX
    Explanations

    words related to participation in agreements or treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atura
    -0.16
    /stdc
    -0.15
    729
    -0.14
    eree
    -0.14
    Clip
    -0.14
     Alias
    -0.14
    erre
    -0.13
    pedo
    -0.13
    irit
    -0.13
    aur
    -0.13
    POSITIVE LOGITS
    æŃ
    0.16
     _______,
    0.16
     majority
    0.15
     bulk
    0.14
     Ø¥ÙĦا
    0.14
     Roberts
    0.13
    bulk
    0.13
    άÏĥ
    0.13
    .Atomic
    0.13
     busy
    0.13
    Act Density 0.279%

    No Known Activations