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

    Neuronpedia

    INDEX
    Explanations

    words related to injuries sustained by individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions or the word "and" indicating a series of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wow
    -0.95
    Fuck
    -0.82
    itans
    -0.79
    Think
    -0.77
    æĥ
    -0.76
    Imagine
    -0.75
    æѦ
    -0.73
    uta
    -0.73
    kiss
    -0.72
    aclysm
    -0.72
    POSITIVE LOGITS
     underwent
    0.98
     therefore
    0.95
     fielded
    0.89
     possibly
    0.86
     contributed
    0.85
     consequently
    0.85
     expects
    0.83
     transported
    0.82
     escorted
    0.82
     awaiting
    0.81
    Act Density 0.362%

    No Known Activations