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

    Neuronpedia

    INDEX
    Explanations

    verbs related to extension or expansion

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to extension or expansion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utan
    -0.84
    EStream
    -0.76
    uki
    -0.66
    beck
    -0.65
    mong
    -0.64
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.62
    inton
    -0.60
    zin
    -0.59
     Diesel
    -0.59
    Eng
    -0.59
    POSITIVE LOGITS
     boundaries
    1.00
     scope
    0.98
     bounds
    0.98
    izons
    0.96
     hor
    0.84
    radius
    0.81
     radius
    0.81
     horizontally
    0.79
     circle
    0.78
     diameter
    0.76
    Act Density 0.180%

    No Known Activations