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

    Neuronpedia

    INDEX
    Explanations

    references to romantic relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to romantic themes or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.93
    avis
    -0.93
    ktop
    -0.84
    Downloadha
    -0.83
    */(
    -0.82
    ulhu
    -0.82
    ividual
    -0.80
    paio
    -0.78
    ldon
    -0.78
    redd
    -0.72
    POSITIVE LOGITS
    ized
    0.95
    ization
    0.88
    istic
    0.88
     romantic
    0.87
    izing
    0.87
    ties
    0.85
    istically
    0.83
     Romance
    0.76
    isation
    0.76
     comed
    0.76
    Act Density 0.013%

    No Known Activations