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

    Neuronpedia

    INDEX
    Explanations

    items and their specifications or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aliado
    -0.32
    lehre
    -0.31
    awaiter
    -0.31
     témoins
    -0.29
     prospet
    -0.29
     conseguenze
    -0.28
     samlet
    -0.28
    état
    -0.28
     driving
    -0.27
     språk
    -0.27
    POSITIVE LOGITS
     versions
    0.71
    ConstraintMaker
    0.66
    ModelAdmin
    0.66
     Versions
    0.65
     version
    0.63
     ujednoznacz
    0.63
    delwed
    0.63
     versiones
    0.60
    Versions
    0.59
     versión
    0.59
    Act Density 0.365%

    No Known Activations