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

    Neuronpedia

    INDEX
    Explanations

    format indicators or placeholders within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.57
    SharedCtor
    -0.57
    Filmografie
    -0.54
    glDelete
    -0.53
     noqa
    -0.52
    jfree
    -0.52
    amse
    -0.52
    énario
    -0.51
    writeFieldEnd
    -0.50
    ewear
    -0.50
    POSITIVE LOGITS
    MemoryWarning
    0.82
     ***!
    0.77
     myſelf
    0.71
    ſelves
    0.69
    .*")]
    0.68
     kolei
    0.66
    <td>
    0.63
    ंदीखरीदारी
    0.62
    itm
    0.61
     themſelves
    0.61
    Act Density 0.064%

    No Known Activations