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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating past experiences or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )++;
    -0.50
     mijne
    -0.43
    ksikon
    -0.42
     Baumwolle
    -0.41
     âmes
    -0.41
    AnchorStyles
    -0.40
     čier
    -0.40
     bijoux
    -0.40
    󠁮
    -0.39
    usermodel
    -0.38
    POSITIVE LOGITS
     been
    0.79
    Been
    0.78
     Been
    0.77
    been
    0.73
     BEEN
    0.67
     vært
    0.62
    一直
    0.57
     sido
    0.56
     været
    0.53
    一直在
    0.53
    Act Density 0.519%

    No Known Activations