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

    Neuronpedia

    INDEX
    Explanations

    personal interactions and relationships, particularly involving statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant actions and emotional states involving characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ements
    -0.74
    solete
    -0.67
     Coliseum
    -0.65
     hindsight
    -0.64
    imental
    -0.64
    uay
    -0.64
    espie
    -0.63
    querque
    -0.63
    ement
    -0.63
     sqor
    -0.62
    POSITIVE LOGITS
     herself
    1.80
     husband
    1.10
     boyfriend
    0.96
     maid
    0.94
     breasts
    0.93
     pregnant
    0.91
     nurse
    0.88
     childbirth
    0.87
     maternity
    0.87
     Louise
    0.85
    Act Density 0.876%

    No Known Activations