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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical procedures and treatments

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate conclusion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extinct
    -0.69
     defe
    -0.66
     independ
    -0.62
     sustainable
    -0.61
    stal
    -0.60
    izoph
    -0.60
     agent
    -0.59
    ulic
    -0.58
     activ
    -0.58
     unders
    -0.57
    POSITIVE LOGITS
     However
    1.05
     Specifically
    1.05
     Especially
    0.98
     Though
    0.98
     Particularly
    0.96
     Those
    0.95
     While
    0.95
     Previously
    0.95
     Instead
    0.94
     Although
    0.94
    Act Density 0.766%

    No Known Activations