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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial and technical topics

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to financial crises and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    `.
    -0.62
    clusively
    -0.59
    ".
    -0.58
    ],"
    -0.56
     ASAP
    -0.56
    '.
    -0.56
    $.
    -0.56
     unnecessarily
    -0.55
    ratom
    -0.54
     Calais
    -0.52
    POSITIVE LOGITS
     meanwhile
    0.67
     corresponds
    0.57
     seemed
    0.57
     tends
    0.57
     retains
    0.54
     disappears
    0.54
     forbids
    0.52
     consists
    0.52
     seems
    0.52
     flowed
    0.51
    Act Density 1.721%

    No Known Activations