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

    Neuronpedia

    INDEX
    Explanations

    phrases related to automation and modernization

    oai_token-act-pair · gpt-3.5-turbo

    instances of non-standard character sequences or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -1.01
     RAD
    -0.74
    è£ħ
    -0.73
     Palest
    -0.73
    çĶ°
    -0.65
    ozy
    -0.63
    GY
    -0.63
    ;;;;;;;;;;;;
    -0.62
     Jed
    -0.61
    DragonMagazine
    -0.61
    POSITIVE LOGITS
    ¢
    0.93
    should
    0.89
    ought
    0.82
    ¤
    0.81
    could
    0.80
    /
    0.80
    ¼
    0.79
    Ĵ
    0.78
    nation
    0.75
    ump
    0.75
    Act Density 0.289%

    No Known Activations