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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "acting" or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     im
    -0.17
    aggi
    -0.15
     Rosenstein
    -0.15
     Bucc
    -0.14
     Im
    -0.14
    es
    -0.14
    esen
    -0.14
    adata
    -0.14
     Eag
    -0.14
     incon
    -0.14
    POSITIVE LOGITS
    renom
    0.17
    rema
    0.16
    ahu
    0.15
    902
    0.15
     premi
    0.15
    ossa
    0.15
    FG
    0.14
    @nate
    0.14
    æĶ
    0.14
    nem
    0.14
    Act Density 0.005%

    No Known Activations