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

    Neuronpedia

    INDEX
    Explanations

    phrases related to existential feelings and reflections on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sucedido
    -0.30
     ocurrido
    -0.28
     haberse
    -0.28
     bēr
    -0.27
     kajian
    -0.26
     habido
    -0.25
     kości
    -0.25
     conmemor
    -0.25
     régulier
    -0.25
     oídos
    -0.25
    POSITIVE LOGITS
    <unused28>
    1.09
    <unused8>
    1.09
    <unused43>
    1.09
    <unused79>
    1.09
    <unused41>
    1.09
    <unused42>
    1.09
    <unused3>
    1.08
    <unused14>
    1.08
    [@BOS@]
    1.08
    <pad>
    1.08
    Act Density 0.947%

    No Known Activations