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

    Neuronpedia

    INDEX
    Explanations

    personal possessive pronouns and their context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .*")]
    -0.63
     itſelf
    -0.60
     autorytatywna
    -0.60
    GEBURTS
    -0.56
    findpost
    -0.55
    Personensuche
    -0.52
    AddHtmlAttribute
    -0.52
     myſelf
    -0.52
    AxisAlignment
    -0.51
    BeginContext
    -0.50
    POSITIVE LOGITS
     behalf
    0.73
     expense
    0.54
     approval
    0.53
     presence
    0.53
     disposal
    0.51
     favor
    0.51
     favour
    0.49
     liking
    0.49
     direction
    0.48
     mercy
    0.48
    Act Density 0.473%

    No Known Activations