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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural instructions or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     להם
    -0.56
    ,
    -0.55
    👈
    -0.54
    டும்
    -0.52
     po
    -0.51
     eléctricos
    -0.50
     –
    -0.49
    numerusform
    -0.49
    apie
    -0.49
    ซ์
    -0.49
    POSITIVE LOGITS
     itſelf
    1.05
     Anſ
    0.94
     myſelf
    0.93
    ſelves
    0.91
    دانشنامهٔ
    0.90
     Houſe
    0.87
     Majefty
    0.85
    ſelf
    0.84
    󠁧
    0.81
    neſs
    0.81
    Act Density 0.112%

    No Known Activations