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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.71
     AssemblyProduct
    -0.59
     skak
    -0.57
    polazione
    -0.55
    Aholisi
    -0.54
    olé
    -0.52
    piram
    -0.51
     Mercurio
    -0.50
     Rheinland
    -0.50
     laft
    -0.49
    POSITIVE LOGITS
    <bos>
    0.58
    iprot
    0.55
    fjspx
    0.53
    ReusableCell
    0.52
     snippetHide
    0.52
     numberWith
    0.49
    featureID
    0.47
    setopt
    0.46
    adapted
    0.45
     tùy
    0.45
    Act Density 0.911%

    No Known Activations