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

    Neuronpedia

    INDEX
    Explanations

    words related to fact-checking and performance evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to added taxes and scoring in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.78
    oru
    -0.77
    skill
    -0.74
    owe
    -0.72
    nih
    -0.72
    itu
    -0.71
    byn
    -0.70
    ãĤ¨ãĥ«
    -0.69
    bring
    -0.69
    ripp
    -0.69
    POSITIVE LOGITS
     lect
    0.79
     institute
    0.74
     citations
    0.66
     hotline
    0.65
    illance
    0.65
     deduction
    0.62
     enclave
    0.60
     abbre
    0.60
     referees
    0.60
     inhibitor
    0.60
    Act Density 0.205%

    No Known Activations