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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that indicate preference or substitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ers
    -0.51
    A
    -0.51
    L
    -0.50
     británica
    -0.48
     Pliny
    -0.48
    y
    -0.47
    1
    -0.47
    V
    -0.45
     roux
    -0.45
    2
    -0.44
    POSITIVE LOGITS
    ValueGeneration
    0.94
     كومونز
    0.90
     <<<<<<<<<<<<<<
    0.89
    RectangleBorder
    0.88
    EndGlobalSection
    0.88
     дописавши
    0.87
    adpleegd
    0.84
     <>",
    0.82
    setVerticalGroup
    0.82
    oredCriteria
    0.81
    Act Density 0.141%

    No Known Activations