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

    Neuronpedia

    INDEX
    Explanations

    text related to legal matters and obligations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "by" in various contexts, indicating dependence or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.87
    ascript
    -0.84
    puter
    -0.75
    Ì
    -0.71
    illance
    -0.70
    ival
    -0.69
    ymes
    -0.69
    ãĥ´ãĤ¡
    -0.69
    earchers
    -0.67
    ussion
    -0.67
    POSITIVE LOGITS
     virtue
    1.05
     successive
    0.82
    products
    0.78
     employers
    0.76
     contractors
    0.75
     vendors
    0.75
    laws
    0.74
     various
    0.74
     adversaries
    0.73
     those
    0.72
    Act Density 0.152%

    No Known Activations