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

    Neuronpedia

    INDEX
    Explanations

    mentions of old or outdated items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.84
    utterstock
    -0.82
    phasis
    -0.82
    ONSORED
    -0.78
    illation
    -0.77
    Ĥİ
    -0.76
     athlet
    -0.76
    ILA
    -0.76
    otos
    -0.75
    ãĤ´ãĥ³
    -0.74
    POSITIVE LOGITS
     fashioned
    1.14
     old
    0.90
    rums
    0.80
     acquaintance
    0.79
    old
    0.78
    school
    0.75
     timers
    0.73
    boy
    0.73
     school
    0.73
     boy
    0.73
    Act Density 0.021%

    No Known Activations