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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly related to measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realisation
    -0.89
     optimised
    -0.81
     localisation
    -0.80
     realising
    -0.80
     standardised
    -0.77
     optimisation
    -0.76
     realised
    -0.75
     realise
    -0.74
     splendour
    -0.73
     visualisation
    -0.73
    POSITIVE LOGITS
    Chham
    0.54
     gallons
    0.50
     voeten
    0.45
    InitVars
    0.44
     millas
    0.44
     colonias
    0.44
     ounces
    0.44
     zijne
    0.43
    gallon
    0.43
     gallon
    0.43
    Act Density 0.620%

    No Known Activations