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

    Neuronpedia

    INDEX
    Explanations

    concepts related to understanding and reflecting on past experiences to improve the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumii
    -0.55
    adon
    -0.55
    BASEPATH
    -0.52
    chon
    -0.48
     Mac
    -0.48
    rinth
    -0.47
    rips
    -0.45
    quirrel
    -0.45
    insic
    -0.45
     Rus
    -0.45
    POSITIVE LOGITS
     future
    0.99
    future
    0.98
    FUTURE
    0.88
    Future
    0.86
    これからの
    0.83
    これから
    0.83
     künf
    0.81
     futuras
    0.81
     FUTURE
    0.81
    今後の
    0.80
    Act Density 0.446%

    No Known Activations