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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology, such as software and hardware words

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various forms of social and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĦ
    -0.75
    ãģĻ
    -0.73
    AME
    -0.70
    #$
    -0.70
    $.
    -0.69
    ãģ¾
    -0.68
    Ùĩ
    -0.68
    Imagine
    -0.67
    Ö¼
    -0.67
    Common
    -0.67
    POSITIVE LOGITS
     aside
    0.72
     fixme
    0.68
     alert
    0.66
     huh
    0.65
     meanwhile
    0.65
     Edit
    0.63
     Sonia
    0.62
     --------------------
    0.62
     technician
    0.61
     logs
    0.61
    Act Density 0.619%

    No Known Activations