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

    Neuronpedia

    INDEX
    Explanations

    the term "mon" or variations related to "monomer" or "monopole"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.81
     itſelf
    -0.81
    <unused41>
    -0.80
    <unused3>
    -0.80
    <unused42>
    -0.80
    <unused43>
    -0.79
    <unused47>
    -0.79
    <unused74>
    -0.79
    <unused51>
    -0.79
    [@BOS@]
    -0.79
    POSITIVE LOGITS
    ute
    0.57
     further
    0.56
    imp
    0.56
    mon
    0.54
     tailored
    0.52
     shot
    0.47
     tailor
    0.47
    tail
    0.46
     =
    0.43
    TEXTURE
    0.42
    Act Density 0.366%

    No Known Activations