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

    Neuronpedia

    INDEX
    Explanations

    phrases related to supporter options or contributions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueGenerated
    -0.79
     pleaſure
    -0.72
     varandra
    -0.71
    Portale
    -0.69
     '\\;'
    -0.69
     houſe
    -0.68
    ContentAsync
    -0.67
     Efq
    -0.67
    RenderAtEndOf
    -0.66
    traje
    -0.66
    POSITIVE LOGITS
     donation
    0.58
     donating
    0.56
     donate
    0.54
     Patreon
    0.53
     donations
    0.52
    Donate
    0.52
     Donations
    0.49
     Privacidade
    0.48
     considered
    0.47
     Donate
    0.47
    Act Density 0.025%

    No Known Activations