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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to concealment and secrecy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AdapterView
    -0.82
    MigrationBuilder
    -0.77
     CWE
    -0.71
     strokes
    -0.65
    WithFormat
    -0.62
    HttpPost
    -0.61
    <code>
    -0.60
     Oester
    -0.60
     كمان
    -0.60
     }}">
    -0.60
    POSITIVE LOGITS
     hide
    1.47
     hiding
    1.47
     hides
    1.43
     Hiding
    1.38
     Hide
    1.37
    hiding
    1.35
     Hidden
    1.34
     hid
    1.33
     hidden
    1.31
    hide
    1.29
    Act Density 0.089%

    No Known Activations