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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and terms indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ResumeLayout
    -0.69
     MonoBehaviour
    -0.68
    gwin
    -0.67
    atissimo
    -0.67
    consulté
    -0.66
    esía
    -0.64
    InjectAttribute
    -0.62
    didReceive
    -0.62
    PostExecute
    -0.61
    ölcs
    -0.61
    POSITIVE LOGITS
     stronger
    1.35
     clearer
    1.34
     harder
    1.31
     tighter
    1.28
     safer
    1.28
     nicer
    1.27
     better
    1.26
     stiffer
    1.26
    better
    1.26
     happier
    1.26
    Act Density 1.097%

    No Known Activations