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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and suggestions for improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بÙĪابة
    -0.17
    ijn
    -0.15
     Hem
    -0.15
    rint
    -0.14
    esor
    -0.14
    太éĥİ
    -0.14
     fond
    -0.14
    ngo
    -0.14
    ê¸ī
    -0.14
    ORT
    -0.13
    POSITIVE LOGITS
     future
    0.27
     how
    0.25
     бÑĥдÑĥÑī
    0.24
    å¦Ĥä½ķ
    0.24
    future
    0.22
     cómo
    0.20
    æľªæĿ¥
    0.20
    .future
    0.19
     Future
    0.19
    how
    0.19
    Act Density 0.103%

    No Known Activations