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

    Neuronpedia

    INDEX
    Explanations

    numbers or special character sequences that follow a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with specific data points or entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iful
    -0.79
    jad
    -0.78
     Solitaire
    -0.75
    cape
    -0.75
    igmat
    -0.75
    arnaev
    -0.74
    arette
    -0.73
    print
    -0.73
    heet
    -0.73
     Hots
    -0.72
    POSITIVE LOGITS
    mph
    0.81
     ILCS
    0.79
    emale
    0.75
    rf
    0.70
    lbs
    0.69
    interstitial
    0.66
    ĺħ
    0.66
     amino
    0.66
    nd
    0.65
    RF
    0.65
    Act Density 0.026%

    No Known Activations