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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs or phrases related to taking action or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.87
     uſed
    -0.84
     Efq
    -0.82
     EEC
    -0.81
     ſhe
    -0.76
     fubject
    -0.76
    gisi
    -0.75
     itſelf
    -0.74
     Shakspeare
    -0.73
     themſelves
    -0.73
    POSITIVE LOGITS
     zu
    1.84
     Zu
    1.12
    Zu
    1.09
    zu
    1.06
     zum
    1.00
     Zum
    0.93
    Zum
    0.89
     ZU
    0.84
    zus
    0.77
     zur
    0.77
    Act Density 0.032%

    No Known Activations