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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.62
     незавершена
    -0.62
    المناصب
    -0.54
    SearchTree
    -0.53
    ParallelGroup
    -0.51
    printLine
    -0.51
     springfox
    -0.49
    addPreferredGap
    -0.48
     volando
    -0.48
    IndentedString
    -0.48
    POSITIVE LOGITS
    findpost
    0.73
     ProtoMessage
    0.63
     own
    0.59
    jonen
    0.57
    seits
    0.56
     fingers
    0.56
    iffen
    0.55
    ntö
    0.52
    μων
    0.52
    RotationOrder
    0.51
    Act Density 0.196%

    No Known Activations