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

    Neuronpedia

    INDEX
    Explanations

    dates written in "Month Day" format

    oai_token-act-pair · gpt-3.5-turbo

    dates with the prefix "Jun" indicating days in June

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.96
     Panic
    -0.69
     Oblivion
    -0.68
    toe
    -0.65
    ansas
    -0.62
     Trials
    -0.61
     reconciliation
    -0.61
    finder
    -0.61
    ר
    -0.60
     Slam
    -0.60
    POSITIVE LOGITS
    eteenth
    1.35
    cture
    1.32
    iors
    1.32
    iper
    1.22
    ctions
    1.20
    ipers
    1.15
    ior
    1.07
    pei
    1.07
    ctive
    0.96
    IOR
    0.93
    Act Density 0.021%

    No Known Activations