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

    Neuronpedia

    INDEX
    Explanations

    words related to components or types of valves and similar mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    net
    -0.17
    ner
    -0.17
    ctor
    -0.17
    misc
    -0.16
    nero
    -0.16
    nt
    -0.16
    tron
    -0.15
    ark
    -0.15
    emon
    -0.14
    nic
    -0.14
    POSITIVE LOGITS
    ighbour
    0.21
    utral
    0.21
    uve
    0.20
    ighb
    0.20
    ymoon
    0.19
    ering
    0.19
    jad
    0.19
    ymous
    0.18
    ighbours
    0.18
    berger
    0.18
    Act Density 0.048%

    No Known Activations