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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [-
    -0.66
    andise
    -0.64
    ãģ®ç
    -0.63
    earch
    -0.61
    ãĤ´
    -0.61
    mons
    -0.61
     clearance
    -0.60
     Clear
    -0.59
    ".[
    -0.58
    "[
    -0.58
    POSITIVE LOGITS
    rosso
    0.85
     somew
    0.78
     misunder
    0.74
     someday
    0.72
     typo
    0.72
    rist
    0.71
    tim
    0.69
     inadvert
    0.66
     quir
    0.65
     wiser
    0.64
    Act Density 0.278%

    No Known Activations