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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to negative conditions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of poverty and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategory
    -1.04
    CU
    -0.76
    auer
    -0.74
    ubi
    -0.73
    CRE
    -0.70
    thus
    -0.69
    TI
    -0.69
    ULAR
    -0.68
    natureconservancy
    -0.68
    IDA
    -0.67
    POSITIVE LOGITS
     quality
    0.85
    dies
    0.83
     luck
    0.82
    die
    0.82
    luck
    0.82
     souls
    0.82
    quality
    0.81
     grades
    0.81
     performers
    0.79
    lings
    0.78
    Act Density 0.041%

    No Known Activations