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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concealment or hiding information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AdapterView
    -0.69
     CWE
    -0.67
    ContentAsync
    -0.64
    PyExc
    -0.63
     /\.
    -0.61
     consultato
    -0.61
    டுத்த
    -0.60
    RESUM
    -0.59
     كمان
    -0.58
    MigrationBuilder
    -0.58
    POSITIVE LOGITS
     hide
    1.71
     hides
    1.69
     hiding
    1.69
     Hide
    1.64
     Hiding
    1.62
    hiding
    1.57
    Hide
    1.52
    hide
    1.52
     hid
    1.48
    Hiding
    1.44
    Act Density 0.084%

    No Known Activations