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

    Neuronpedia

    INDEX
    Explanations

    mentions of barrels

    oai_token-act-pair · gpt-3.5-turbo

    references to barrels and related quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urally
    -0.87
    ctive
    -0.77
    inx
    -0.72
    atem
    -0.70
    egg
    -0.70
    pter
    -0.69
    amaru
    -0.68
    reme
    -0.67
    apore
    -0.67
     Debor
    -0.66
    POSITIVE LOGITS
     hitch
    0.87
     door
    0.81
     empt
    0.80
    mith
    0.79
    oil
    0.77
     doors
    0.77
     lid
    0.77
    Fill
    0.74
     barrels
    0.74
    door
    0.73
    Act Density 0.090%

    No Known Activations