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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss and decline

    oai_token-act-pair · gpt-3.5-turbo

    references to loss and its impacts on various aspects of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IOR
    -0.70
    INO
    -0.65
    IPS
    -0.64
    Exit
    -0.64
    Ir
    -0.64
    DIT
    -0.63
    INC
    -0.62
    Whe
    -0.62
     Quarterly
    -0.61
    Statement
    -0.60
    POSITIVE LOGITS
     virginity
    1.11
     tiss
    0.85
    elsen
    0.79
     dignity
    0.77
     sanity
    0.76
     pursu
    0.74
     grasp
    0.74
     altogether
    0.72
     composure
    0.71
     traction
    0.70
    Act Density 0.213%

    No Known Activations