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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ing
    -0.70
    LogFactory
    -0.70
     Mog
    -0.69
    /**
    -0.68
    mación
    -0.67
     bact
    -0.67
    ModelForm
    -0.67
    toggler
    -0.66
    Rig
    -0.66
     jouets
    -0.66
    POSITIVE LOGITS
     appreciate
    1.41
    reciate
    1.33
     appreci
    1.25
     appreciation
    1.23
     Appreciate
    1.20
     appreciates
    1.19
    reciation
    1.17
    Appreciate
    1.17
    appreciated
    1.17
     appreciated
    1.16
    Act Density 0.007%

    No Known Activations