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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions and experiences related to personal reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.68
     Hezbollah
    -0.65
     jointly
    -0.65
     descendants
    -0.63
     Islamists
    -0.63
    ween
    -0.62
     respectively
    -0.62
     2024
    -0.61
    idates
    -0.59
    cedes
    -0.59
    POSITIVE LOGITS
     myself
    1.13
    ãĤ¦ãĤ¹
    0.82
     researching
    0.77
     feeling
    0.74
     wondering
    0.72
     imagining
    0.70
     noticing
    0.69
     aback
    0.69
     my
    0.68
    ntil
    0.68
    Act Density 0.646%

    No Known Activations