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

    Neuronpedia

    INDEX
    Explanations

    instances and discussions of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heureuse
    -0.75
    டன்
    -0.74
     veicolo
    -0.72
     cathédrale
    -0.71
     indeks
    -0.70
    martre
    -0.69
     MacMillan
    -0.69
     hinweg
    -0.69
     malen
    -0.68
     veilig
    -0.68
    POSITIVE LOGITS
     talk
    1.76
    talk
    1.69
     TALK
    1.61
     Talk
    1.57
     talks
    1.57
     talked
    1.52
    Talk
    1.46
     talking
    1.46
     Talks
    1.44
    TALK
    1.42
    Act Density 0.050%

    No Known Activations