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

    Neuronpedia

    INDEX
    Explanations

    words related to tunnels

    oai_token-act-pair · gpt-3.5-turbo

    references to tunnels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberties
    -0.72
    aign
    -0.66
    yright
    -0.66
    orian
    -0.65
    metics
    -0.65
    iscons
    -0.62
    oln
    -0.61
     welf
    -0.60
    FUL
    -0.60
    ãĤŃ
    -0.59
    POSITIVE LOGITS
     dug
    0.89
     tunnels
    0.88
     tunnel
    0.87
    vision
    0.84
    WAY
    0.82
    geon
    0.81
     boring
    0.81
     entrances
    0.81
     junction
    0.79
    nels
    0.78
    Act Density 0.055%

    No Known Activations