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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global, national, or overall scope and impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographical scope or reach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actic
    -0.74
    ppe
    -0.67
    itarian
    -0.66
    ometric
    -0.65
    itialized
    -0.65
    bern
    -0.65
    itar
    -0.65
    ocratic
    -0.62
    msg
    -0.62
    utive
    -0.62
    POSITIVE LOGITS
    aneously
    0.77
    abouts
    0.76
    without
    0.71
    ntil
    0.70
     mornings
    0.68
     without
    0.67
     srfAttach
    0.66
     throughout
    0.66
     cheaply
    0.66
     asleep
    0.66
    Act Density 0.179%

    No Known Activations