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

    Neuronpedia

    INDEX
    Explanations

    negative traits in relationships, such as dishonesty and irresponsibility

    oai_token-act-pair · gpt-3.5-turbo

    themes related to romantic relationships and dating dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chavez
    -0.83
     loader
    -0.81
     Cato
    -0.79
     respir
    -0.75
     Atkinson
    -0.74
     Scourge
    -0.73
     redist
    -0.73
    ensor
    -0.73
    ZA
    -0.72
     Agriculture
    -0.71
    POSITIVE LOGITS
     Tinder
    1.97
     Dating
    1.82
     dating
    1.75
     monog
    1.69
     flirt
    1.59
     romantic
    1.53
     romance
    1.50
     girlfriends
    1.38
     boyfriend
    1.38
    dating
    1.38
    Act Density 0.628%

    No Known Activations