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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.72
    parsedMessage
    -0.70
     betweenstory
    -0.70
    httphttps
    -0.63
    Хьажоргаш
    -0.63
    Datuak
    -0.61
    richTextPanel
    -0.59
    aarrggbb
    -0.59
    writerow
    -0.58
     المعيارى
    -0.58
    POSITIVE LOGITS
    img
    0.47
     Wonder
    0.42
    Wonder
    0.41
    ID
    0.40
     fade
    0.39
    Eisen
    0.36
     wondering
    0.35
     WONDER
    0.34
    fade
    0.34
     easier
    0.34
    Act Density 0.110%

    No Known Activations