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

    Neuronpedia

    INDEX
    Explanations

    references to debates and discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jar
    -0.54
    pit
    -0.51
    rob
    -0.51
    NIL
    -0.50
    circ
    -0.50
    deg
    -0.50
    dart
    -0.50
    tid
    -0.50
     NIL
    -0.49
    ars
    -0.49
    POSITIVE LOGITS
     enfans
    0.87
     Monfieur
    0.84
     desmotivaciones
    0.81
     Houſe
    0.81
     navideño
    0.79
     navideños
    0.77
     myſelf
    0.75
     houſe
    0.75
     näytte
    0.73
     Anſ
    0.73
    Act Density 0.248%

    No Known Activations