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

    Neuronpedia

    INDEX
    Explanations

    references to tasks or activities related to homework

    oai_token-act-pair · gpt-3.5-turbo

    references to academic tasks and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riott
    -0.80
     ambassadors
    -0.76
    itol
    -0.75
    ocal
    -0.71
     Osw
    -0.69
     marginal
    -0.66
    vir
    -0.65
     Celebr
    -0.64
    por
    -0.63
     embassies
    -0.61
    POSITIVE LOGITS
     homework
    1.19
    heet
    0.96
     remed
    0.87
     assignment
    0.87
     assignments
    0.77
    essor
    0.76
    ornings
    0.75
    essors
    0.75
    ussion
    0.73
    work
    0.71
    Act Density 0.012%

    No Known Activations