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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical ratings or series codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../
    -0.19
     صÙĦÙī
    -0.17
    nemonic
    -0.16
    ned
    -0.15
    .weixin
    -0.15
    271
    -0.15
    ãģĤãĤĬ
    -0.14
    ulumi
    -0.14
    308
    -0.14
    ãģĤãģ£ãģŁ
    -0.14
    POSITIVE LOGITS
    rd
    0.49
    -quarters
    0.36
    ../../../
    0.26
     rd
    0.24
    RD
    0.23
    -four
    0.23
    peat
    0.22
    fold
    0.22
    ï¸ı
    0.22
    -dimensional
    0.20
    Act Density 0.239%

    No Known Activations