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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and symbols, particularly in contexts where they denote scores or data related to age and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.64
     bait
    -0.63
    aida
    -0.62
     hol
    -0.62
     raft
    -0.62
     impuls
    -0.61
     axe
    -0.61
     fuzzy
    -0.60
     scissors
    -0.59
     cue
    -0.59
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.88
     MPH
    0.87
    254
    0.83
     percentile
    0.77
    949
    0.77
    percent
    0.76
    degree
    0.76
    ãĥīãĥ©ãĤ´ãĥ³
    0.76
    030
    0.75
    660
    0.74
    Act Density 0.264%

    No Known Activations