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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Durbin" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to deer and urban locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ented
    -0.88
    ynt
    -0.87
    enta
    -0.86
    pocket
    -0.83
    ertodd
    -0.82
    ept
    -0.82
    ommod
    -0.81
    yang
    -0.80
    colo
    -0.76
    oho
    -0.75
    POSITIVE LOGITS
     confir
    0.74
    udeau
    0.72
    manship
    0.64
    GBT
    0.64
    lishes
    0.62
    monkey
    0.61
    escent
    0.60
    DEBUG
    0.58
     stim
    0.58
    mint
    0.58
    Act Density 0.049%

    No Known Activations