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

    Neuronpedia

    INDEX
    Explanations

    the concept of "inverse relationships" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grüße
    -0.46
     franquicia
    -0.45
     rodríguez
    -0.43
     sánchez
    -0.42
    Grüße
    -0.40
     ceremonia
    -0.40
    cluster
    -0.40
     ruban
    -0.39
     RSSSF
    -0.39
    Slots
    -0.39
    POSITIVE LOGITS
     inverse
    0.98
     Inverse
    0.93
     invert
    0.89
    inverse
    0.84
     reverse
    0.81
     inver
    0.81
    Inverse
    0.80
     inverted
    0.80
     Reverse
    0.79
     Inv
    0.77
    Act Density 0.270%

    No Known Activations