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

    Neuronpedia

    INDEX
    Explanations

    phrases using the expression "all sorts of things."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.87
    inion
    -0.73
    aeper
    -0.70
    eka
    -0.67
    esi
    -0.66
     Annotations
    -0.65
     entirety
    -0.65
    ema
    -0.64
    arest
    -0.64
    iano
    -0.63
    POSITIVE LOGITS
     goodies
    0.87
     kinds
    0.86
     imaginable
    0.84
     nasty
    0.83
     havoc
    0.81
     shenanigans
    0.78
    things
    0.77
     fancy
    0.77
    hots
    0.77
     things
    0.76
    Act Density 0.060%

    No Known Activations