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

    Neuronpedia

    INDEX
    Explanations

    structured data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hu
    -0.75
     Turbul
    -0.69
     ha
    -0.64
    MigrationBuilder
    -0.63
     zu
    -0.63
     top
    -0.63
     pu
    -0.62
     con
    -0.61
     un
    -0.61
     z
    -0.61
    POSITIVE LOGITS
     myſelf
    1.20
     Houſe
    1.18
     himſelf
    1.16
     Anſ
    1.15
    ſelf
    1.14
     Jefus
    1.12
    ſelves
    1.10
     itſelf
    1.09
     Eſ
    1.06
     themſelves
    1.05
    Act Density 0.293%

    No Known Activations