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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating progression or development

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress and completion of tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Julius
    -0.64
    States
    -0.62
    Britain
    -0.60
     Contemporary
    -0.59
     Nim
    -0.58
     Proceedings
    -0.57
     Allied
    -0.57
     explains
    -0.56
     Matth
    -0.56
     Electronic
    -0.56
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.79
    wcsstore
    0.77
    ãĥĨ
    0.72
    rontal
    0.70
    ortium
    0.67
    %:
    0.67
    ãĤ£
    0.65
    ãĥ¼ãĤ¯
    0.65
    °
    0.64
    cffffcc
    0.63
    Act Density 0.103%

    No Known Activations