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

    Neuronpedia

    INDEX
    Explanations

    names of specific places followed by an event or program title

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.72
    lins
    -0.71
     suppose
    -0.69
    gans
    -0.68
    coins
    -0.68
    ratulations
    -0.67
    VER
    -0.66
    eal
    -0.65
    cially
    -0.64
    ister
    -0.63
    POSITIVE LOGITS
     outset
    1.27
     unveiling
    1.12
     behest
    1.11
     helm
    1.07
     podium
    1.05
     inauguration
    1.04
     ceremony
    1.04
     inaugural
    1.02
     conference
    1.01
     summit
    0.97
    Act Density 0.126%

    No Known Activations