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

    Neuronpedia

    INDEX
    Explanations

    references to losing something, whether physical objects or abstract concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to loss or deprivation experienced by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DIT
    -0.81
    Exit
    -0.73
    Bloomberg
    -0.71
    GROUP
    -0.68
    Ir
    -0.67
    INC
    -0.67
    INFO
    -0.66
    Whe
    -0.65
    INO
    -0.64
    Average
    -0.64
    POSITIVE LOGITS
     virginity
    1.14
     credibility
    0.81
     traction
    0.78
     tiss
    0.77
     momentum
    0.76
     dignity
    0.74
     sanity
    0.71
     freedoms
    0.70
     spont
    0.69
     altogether
    0.69
    Act Density 0.165%

    No Known Activations