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

    Neuronpedia

    INDEX
    Explanations

    terms related to the act of putting things together or constructing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fet
    -0.68
    null
    -0.67
    etheless
    -0.64
    terness
    -0.64
    bler
    -0.64
    cas
    -0.63
    few
    -0.63
    tta
    -0.62
    mia
    -0.62
    nton
    -0.62
    POSITIVE LOGITS
    eering
    1.02
    ÃįÃį
    0.90
     assemb
    0.88
     assemble
    0.86
     assembled
    0.85
    ENTS
    0.85
    eers
    0.85
    idable
    0.79
    ALLY
    0.78
     assembling
    0.77
    Act Density 0.013%

    No Known Activations