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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposedly
    -0.63
     supposed
    -0.55
     allegedly
    -0.51
     supuestamente
    -0.49
     suelen
    -0.48
     ostensibly
    -0.47
     suele
    -0.47
    odd
    -0.46
    cripciones
    -0.45
     tils
    -0.45
    POSITIVE LOGITS
     importance
    0.88
     communities
    0.81
    importance
    0.79
     professionalism
    0.79
    Geplaatst
    0.77
     community
    0.77
     mission
    0.76
     spirit
    0.76
     teamwork
    0.74
     traditions
    0.73
    Act Density 0.289%

    No Known Activations